<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://arxiv.org/abs/1312.6055v3"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2502.07192"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2504.07092"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2601.21766"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1208.0482"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.07391"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2302.06457"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2410.04480"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2408.05395"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2502.12717"/>
	<rdf:li rdf:resource="https://www.science.org/doi/10.1126/science.adv7924"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2407.05991"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.01628"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2507.10560"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2512.23146"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2403.15297"/>
	<rdf:li rdf:resource="https://machinelearning.apple.com/research/illusion-of-thinking"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11047-025-10028-7"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2505.16217"/>
	<rdf:li rdf:resource="https://www.pnas.org/doi/10.1073/pnas.0710743106"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/s41467-021-25123-3"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2504.17963"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/s41467-025-59288-y"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2210.02580"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2502.06871"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2502.08021"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2403.14139"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2410.08304"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2503.07811"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2312.12899"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2411.12304"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.08348"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.09780"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2304.13125"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2307.15092"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2401.09501"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2403.16933"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2404.05259"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2205.08954"/>
	<rdf:li rdf:resource="https://www.mdpi.com/2071-1050/11/7/1991"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2310.10692"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2406.11741"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2409.05746"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2404.07150"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2309.03651"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2204.11041"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2109.04175"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2304.10521"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2405.06848"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.02705"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2111.10722"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2405.18029"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.05482"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2407.04491"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.08013"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2310.02227"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2405.17514"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2301.11919"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.04708"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.04962"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=HGsQrD6pPGM"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2208.14567"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2210.14707"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2209.14440"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.04739"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.09179"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.10541"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2205.09438"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1712.07897"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.00666"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/1312.6055v3">
    <title>[1312.6055v3] Unit Tests for Stochastic Optimization</title>
    <dc:date>2026-07-04T13:14:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1312.6055v3</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Optimization by stochastic gradient descent is an important component of many large-scale machine learning algorithms. A wide variety of such optimization algorithms have been devised; however, it is unclear whether these algorithms are robust and widely applicable across many different optimization landscapes. In this paper we develop a collection of unit tests for stochastic optimization. Each unit test rapidly evaluates an optimization algorithm on a small-scale, isolated, and well-understood difficulty, rather than in real-world scenarios where many such issues are entangled. Passing these unit tests is not sufficient, but absolutely necessary for any algorithms with claims to generality or robustness. We give initial quantitative and qualitative results on numerous established algorithms. The testing framework is open-source, extensible, and easy to apply to new algorithms.
]]></description>
<dc:subject>benchmarking operations-research unit-testing performance-measure rather-interesting metaheuristics neural-networks machine-learning to-write-about to-use</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ebbe888f0ef2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unit-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-use"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2502.07192">
    <title>[2502.07192] OscNet: Machine Learning on CMOS Oscillator Networks</title>
    <dc:date>2026-05-26T20:05:20+00:00</dc:date>
    <link>https://arxiv.org/abs/2502.07192</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning and AI have achieved remarkable advancements but at the cost of significant computational resources and energy consumption. This has created an urgent need for a novel, energy-efficient computational fabric to replace the current computing pipeline. Recently, a promising approach has emerged by mimicking spiking neurons in the brain and leveraging oscillators on CMOS for direct computation. In this context, we propose a new and energy efficient machine learning framework implemented on CMOS Oscillator Networks (OscNet). We model the developmental processes of the prenatal brain's visual system using OscNet, updating weights based on the biologically inspired Hebbian rule. This same pipeline is then directly applied to standard machine learning tasks. OscNet is a specially designed hardware and is inherently energy-efficient. Its reliance on forward propagation alone for training further enhances its energy efficiency while maintaining biological plausibility. Simulation validates our designs of OscNet architectures. Experimental results demonstrate that Hebbian learning pipeline on OscNet achieves performance comparable to or even surpassing traditional machine learning algorithms, highlighting its potential as a energy efficient and effective computational paradigm.
]]></description>
<dc:subject>coupled-oscillators nonlinear-dynamics machine-learning neural-networks Hebbian-networks to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:77d9725b322e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coupled-oscillators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Hebbian-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2504.07092">
    <title>[2504.07092] Are We Done with Object-Centric Learning?</title>
    <dc:date>2026-05-25T12:13:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2504.07092</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization, sample-efficient composition, and modeling of structured environments. Most research has focused on developing unsupervised mechanisms that separate objects into discrete slots in the representation space, evaluated using unsupervised object discovery. However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently. This achieves remarkable zero-shot performance on OOD object discovery benchmarks, is scalable to foundation models, and can handle a variable number of slots out-of-the-box. Hence, the goal of OCL methods to obtain object-centric representations has been largely achieved. Despite this progress, a key question remains: How does the ability to separate objects within a scene contribute to broader OCL objectives, such as OOD generalization? We address this by investigating the OOD generalization challenge caused by spurious background cues through the lens of OCL. We propose a novel, training-free probe called Object-Centric Classification with Applied Masks (OCCAM), demonstrating that segmentation-based encoding of individual objects significantly outperforms slot-based OCL methods. However, challenges in real-world applications remain. We provide the toolbox for the OCL community to use scalable object-centric representations, and focus on practical applications and fundamental questions, such as understanding object perception in human cognition. Our code is available here: this https URL.
]]></description>
<dc:subject>image-processing image-segmentation machine-learning rather-interesting algorithms neural-networks image-analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:090aa6203061/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2601.21766">
    <title>[2601.21766] CoFrGeNet: Continued Fraction Architectures for Language Generation</title>
    <dc:date>2026-05-24T17:10:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2601.21766</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function class is named CoFrGeNets - Continued Fraction Generative Networks. We design novel architectural components based on this function class that can replace Multi-head Attention and Feed-Forward Networks in Transformer blocks while requiring much fewer parameters. We derive custom gradient formulations to optimize the proposed components more accurately and efficiently than using standard PyTorch-based gradients. Our components are a plug-in replacement requiring little change in training or inference procedures that have already been put in place for Transformer-based models thus making our approach easy to incorporate in large industrial workflows. We experiment on two very different transformer architectures GPT2-xl (1.5B) and Llama3 (3.2B), where the former we pre-train on OpenWebText and GneissWeb, while the latter we pre-train on the docling data mix which consists of nine different datasets. Results show that the performance on downstream classification, Q\& A, reasoning and text understanding tasks of our models is competitive and sometimes even superior to the original models with 23 to 12 the parameters and shorter pre-training time. We believe that future implementations customized to hardware will further bring out the true potential of our architectures.
]]></description>
<dc:subject>machine-learning representation continued-fractions rational-arithmetic rather-interesting neural-networks performance-measure</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:89915d1a6a54/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:continued-fractions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rational-arithmetic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1208.0482">
    <title>[1208.0482] The concurrent evolution of cooperation and the population structures that support it</title>
    <dc:date>2026-05-24T12:27:54+00:00</dc:date>
    <link>https://arxiv.org/abs/1208.0482</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The evolution of cooperation often depends upon population structure, yet nearly all models of cooperation implicitly assume that this structure remains static. This is a simplifying assumption, because most organisms possess genetic traits that affect their population structure to some degree. These traits, such as a group size preference, affect the relatedness of interacting individuals and hence the opportunity for kin or group selection. We argue that models that do not explicitly consider their evolution cannot provide a satisfactory account of the origin of cooperation, because they cannot explain how the prerequisite population structures arise. Here, we consider the concurrent evolution of genetic traits that affect population structure, with those that affect social behavior. We show that not only does population structure drive social evolution, as in previous models, but that the opportunity for cooperation can in turn drive the creation of population structures that support it. This occurs through the generation of linkage disequilibrium between socio-behavioral and population-structuring traits, such that direct kin selection on social behavior creates indirect selection pressure on population structure. We illustrate our argument with a model of the concurrent evolution of group size preference and social behavior.
]]></description>
<dc:subject>artificial-life machine-learning complexology rather-interesting hey-I-know-this-guy theoretical-biology to-simulate consider:performance-measures coevolution</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b7f06f7b43d1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complexology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coevolution"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.07391">
    <title>[2206.07391] &quot;Why Here and Not There?&quot; -- Diverse Contrasting Explanations of Dimensionality Reduction</title>
    <dc:date>2026-05-24T12:09:35+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.07391</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Dimensionality reduction is a popular preprocessing and a widely used tool in data mining. Transparency, which is usually achieved by means of explanations, is nowadays a widely accepted and crucial requirement of machine learning based systems like classifiers and recommender systems. However, transparency of dimensionality reduction and other data mining tools have not been considered in much depth yet, still it is crucial to understand their behavior -- in particular practitioners might want to understand why a specific sample got mapped to a specific location.
In order to (locally) understand the behavior of a given dimensionality reduction method, we introduce the abstract concept of contrasting explanations for dimensionality reduction, and apply a realization of this concept to the specific application of explaining two dimensional data visualization.
]]></description>
<dc:subject>explanation rather-interesting machine-learning dimension-reduction algorithms performance-measure to-write-about to-do</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:50665668209e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2302.06457">
    <title>[2302.06457] A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms</title>
    <dc:date>2026-05-24T12:06:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2302.06457</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The transistor celebrated its 75th birthday in 2022. The continued scaling of the transistor defined by Moore's Law continues, albeit at a slower pace. Meanwhile, computing demands and energy consumption required by modern artificial intelligence (AI) algorithms have skyrocketed. As an alternative to scaling transistors for general-purpose computing, the integration of transistors with unconventional technologies has emerged as a promising path for domain-specific computing. In this article, we provide a full-stack review of probabilistic computing with p-bits as a representative example of the energy-efficient and domain-specific computing movement. We argue that p-bits could be used to build energy-efficient probabilistic systems, tailored for probabilistic algorithms and applications. From hardware, architecture, and algorithmic perspectives, we outline the main applications of probabilistic computers ranging from probabilistic machine learning and AI to combinatorial optimization and quantum simulation. Combining emerging nanodevices with the existing CMOS ecosystem will lead to probabilistic computers with orders of magnitude improvements in energy efficiency and probabilistic sampling, potentially unlocking previously unexplored regimes for powerful probabilistic algorithms.
]]></description>
<dc:subject>probability-theory probabilistic-computing algorithms rather-interesting machine-learning engineering-design approximation to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:77469b3f11a6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probabilistic-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2410.04480">
    <title>[2410.04480] Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task Generation</title>
    <dc:date>2026-05-24T10:59:46+00:00</dc:date>
    <link>https://arxiv.org/abs/2410.04480</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The ability to think abstractly and reason by analogy is a prerequisite to rapidly adapt to new conditions, tackle newly encountered problems by decomposing them, and synthesize knowledge to solve problems comprehensively. We present TransCoder, a method for solving abstract problems based on neural program synthesis, and conduct a comprehensive analysis of decisions made by the generative module of the proposed architecture. At the core of TransCoder is a typed domain-specific language, designed to facilitate feature engineering and abstract reasoning. In training, we use the programs that failed to solve tasks to generate new tasks and gather them in a synthetic dataset. As each synthetic task created in this way has a known associated program (solution), the model is trained on them in supervised mode. Solutions are represented in a transparent programmatic form, which can be inspected and verified. We demonstrate TransCoder's performance using the Abstract Reasoning Corpus dataset, for which our framework generates tens of thousands of synthetic problems with corresponding solutions and facilitates systematic progress in learning.
]]></description>
<dc:subject>ARC machine-learning genetic-programming neural-networks program-synthesis learning-from-data artificial-intelligence rather-interesting hey-I-know-this-guy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5ba29e7a72c7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ARC"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:program-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2408.05395">
    <title>[2408.05395] The evolution of systems biology and systems medicine: From mechanistic models to uncertainty quantification</title>
    <dc:date>2026-05-24T10:49:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2408.05395</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding the mechanisms of interactions within cells, tissues, and organisms is crucial to driving developments across biology and medicine. Mathematical modeling is an essential tool for simulating biological systems and revealing biochemical regulatory mechanisms. Building on experiments, mechanistic models are widely used to describe small-scale intracellular networks and uncover biochemical mechanisms in healthy and diseased states. The rapid development of high-throughput sequencing techniques and computational tools has recently enabled models that span multiple scales, often integrating signaling, gene regulatory, and metabolic networks. These multiscale models enable comprehensive investigations of cellular networks and thus reveal previously unknown disease mechanisms and pharmacological interventions. Here, we review systems biology models from classical mechanistic models to larger, multiscale models that integrate multiple layers of cellular networks. We introduce several examples of models of hypertrophic cardiomyopathy, exercise, and cancer cell proliferation. Additionally, we discuss methods that increase the certainty and accuracy of model predictions. Integrating multiscale models has become a powerful tool for understanding disease and inspiring drug discoveries by incorporating omics data within the cell and across tissues and organisms.
]]></description>
<dc:subject>systems-biology molecular-machinery medicine medical-technology network-theory pharmaceutical machine-learning rather-interesting models-and-modes reaction-networks systems-thinking</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d028f0a81a52/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-machinery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medicine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medical-technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pharmaceutical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reaction-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-thinking"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2502.12717">
    <title>[2502.12717] Learning the symmetric group: large from small</title>
    <dc:date>2026-05-22T11:20:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2502.12717</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning explorations can make significant inroads into solving difficult problems in pure mathematics. One advantage of this approach is that mathematical datasets do not suffer from noise, but a challenge is the amount of data required to train these models and that this data can be computationally expensive to generate. Key challenges further comprise difficulty in a posteriori interpretation of statistical models and the implementation of deep and abstract mathematical problems.
We propose a method for scalable tasks, by which models trained on simpler versions of a task can then generalize to the full task. Specifically, we demonstrate that a transformer neural-network trained on predicting permutations from words formed by general transpositions in the symmetric group S10 can generalize to the symmetric group S25 with near 100\% accuracy. We also show that S10 generalizes to S16 with similar performance if we only use adjacent transpositions. We employ identity augmentation as a key tool to manage variable word lengths, and partitioned windows for training on adjacent transpositions. Finally we compare variations of the method used and discuss potential challenges with extending the method to other tasks.
]]></description>
<dc:subject>machine-learning mathematical-programming combinatorics neural-networks formal-languages to-understand to-write-about group-theory rather-interesting feature-construction approximation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:062e950d111d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formal-languages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:group-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.science.org/doi/10.1126/science.adv7924">
    <title>DefensePredictor: A machine learning model to discover prokaryotic immune systems | Science</title>
    <dc:date>2026-04-26T12:32:02+00:00</dc:date>
    <link>https://www.science.org/doi/10.1126/science.adv7924</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Bacteria have diverse immune systems that protect them from viral infection, yet the full extent of this diversity remains unknown. Two groups of researchers have now independently developed machine learning and deep learning models that leverage protein sequences and genomic context to predict antiphage defense systems at scale. DeWeirdt et al. developed a model called DefensePredictor and applied it to Escherichia coli, experimentally validating dozens of previously uncharacterized defense systems. Mordret et al. developed several different models and applied them to over 120 million proteins from bacterial genomes, identifying hundreds of thousands of candidate antiphage families, many lacking any prior annotation. Together, these studies reveal that bacterial immunity is far more extensive than previously thought and highlight how such discoveries can inspire powerful biotechnologies. —Di Jiang
]]></description>
<dc:subject>structural-biology machine-learning bioinformatics indistinguishable-from-magic learning-from-data to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d94701a9a214/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indistinguishable-from-magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2407.05991">
    <title>[2407.05991] Multi-Texture Synthesis through Signal Responsive Neural Cellular Automata</title>
    <dc:date>2026-02-21T20:35:23+00:00</dc:date>
    <link>https://arxiv.org/abs/2407.05991</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Neural Cellular Automata (NCA) have proven to be effective in a variety of fields, with numerous biologically inspired applications. One of the fields, in which NCAs perform well is the generation of textures, modelling global patterns from local interactions governed by uniform and coherent rules. This paper aims to enhance the usability of NCAs in texture synthesis by addressing a shortcoming of current NCA architectures for texture generation, which requires separately trained NCA for each individual texture. In this work, we train a single NCA for the evolution of multiple textures, based on individual examples. Our solution provides texture information in the state of each cell, in the form of an internally coded genomic signal, which enables the NCA to generate the expected texture. Such a neural cellular automaton not only maintains its regenerative capability but also allows for interpolation between learned textures and supports grafting techniques. This demonstrates the ability to edit generated textures and the potential for them to merge and coexist within the same automaton. We also address questions related to the influence of the genomic information and the cost function on the evolution of the NCA.
]]></description>
<dc:subject>pattern-formation generative-models generative-art neural-networks rather-interesting cellular-automata image-generation machine-learning note:distance-metric consider:code</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:da851ce41a6f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-formation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-generation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:note:distance-metric"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:code"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.01628">
    <title>[2203.01628] Early Time-Series Classification Algorithms: An Empirical Comparison</title>
    <dc:date>2026-02-20T15:25:10+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.01628</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Early Time-Series Classification (ETSC) is the task of predicting the class of incoming time-series by observing as few measurements as possible. Such methods can be employed to obtain classification forecasts in many time-critical applications. However, available techniques are not equally suitable for every problem, since differentiations in the data characteristics can impact algorithm performance in terms of earliness, accuracy, F1-score, and training time. We evaluate six existing ETSC algorithms on publicly available data, as well as on two newly introduced datasets originating from the life sciences and maritime domains. Our goal is to provide a framework for the evaluation and comparison of ETSC algorithms and to obtain intuition on how such approaches perform on real-life applications. The presented framework may also serve as a benchmark for new related techniques.
]]></description>
<dc:subject>time-series classification machine-learning algorithms rather-interesting to-understand benchmarking</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f60942d80779/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2507.10560">
    <title>[2507.10560] Tangma: A Tanh-Guided Activation Function with Learnable Parameters</title>
    <dc:date>2026-01-18T21:22:37+00:00</dc:date>
    <link>https://arxiv.org/abs/2507.10560</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable parameters: α, which shifts the curve's inflection point to adjust neuron activation, and γ, which adds linearity to preserve weak gradients and improve training stability. Tangma was evaluated on MNIST and CIFAR-10 using custom networks composed of convolutional and linear layers, and compared against ReLU, Swish, and GELU. On MNIST, Tangma achieved the highest validation accuracy of 99.09% and the lowest validation loss, demonstrating faster and more stable convergence than the baselines. On CIFAR-10, Tangma reached a top validation accuracy of 78.15%, outperforming all other activation functions while maintaining a competitive training loss. Tangma also showed improved training efficiency, with lower average epoch runtimes compared to Swish and GELU. These results suggest that Tangma performs well on standard vision tasks and enables reliable, efficient training. Its learnable design gives more control over activation behavior, which may benefit larger models in tasks such as image recognition or language modeling.
]]></description>
<dc:subject>neural-networks machine-learning define-your-terms activation-function toolkit to-write-about to-simulate consider:boolean-classifiers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a7a0171c2fdf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:activation-function"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:toolkit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:boolean-classifiers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2512.23146">
    <title>[2512.23146] A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation</title>
    <dc:date>2026-01-18T21:15:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2512.23146</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a canonical direction obtained via canonical correlation analysis (CCA) of previously observed past-future input pairs, and then rectifies either its positive or negative component. By encoding canonical directions in synaptic weights and temporal filters, ReSUs implement a local, self-supervised algorithm for progressively constructing increasingly complex features.
To evaluate both computational power and biological fidelity, we trained a two-layer ReSU network in a self-supervised regime on translating natural scenes. First-layer units, each driven by a single pixel, developed temporal filters resembling those of Drosophila post-photoreceptor neurons (L1/L2 and L3), including their empirically observed adaptation to signal-to-noise ratio (SNR). Second-layer units, which pooled spatially over the first layer, became direction-selective -- analogous to T4 motion-detecting cells -- with learned synaptic weight patterns approximating those derived from connectomic reconstructions.
Together, these results suggest that ReSUs offer (i) a principled framework for modeling sensory circuits and (ii) a biologically grounded, backpropagation-free paradigm for constructing deep self-supervised neural networks.
]]></description>
<dc:subject>machine-learning algorithms neural-networks representation rather-interesting nonlinear-dynamics collective-behavior to-understand consider:parameter-fitting consider:structure-learning biologically-inspired</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:85f0f61be13d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:parameter-fitting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:structure-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biologically-inspired"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2403.15297">
    <title>[2403.15297] Sphere Neural-Networks for Rational Reasoning</title>
    <dc:date>2025-08-22T12:52:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2403.15297</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The success of Large Language Models (LLMs), e.g., ChatGPT, is witnessed by their planetary popularity, their capability of human-like communication, and also by their steadily improved reasoning performance. However, it remains unclear whether LLMs reason. It is an open problem how traditional neural networks can be qualitatively extended to go beyond the statistic paradigm and achieve high-level cognition. Here, we present a novel qualitative extension by generalising computational building blocks from vectors to spheres. We propose Sphere Neural Networks (SphNNs) for human-like reasoning through model construction and inspection, and develop SphNN for syllogistic reasoning, a microcosm of human rationality. SphNN is a hierarchical neuro-symbolic Kolmogorov-Arnold geometric GNN, and uses a neuro-symbolic transition map of neighbourhood spatial relations to transform the current sphere configuration towards the target. SphNN is the first neural model that can determine the validity of long-chained syllogistic reasoning in one epoch without training data, with the worst computational complexity of O(N). SphNN can evolve into various types of reasoning, such as spatio-temporal reasoning, logical reasoning with negation and disjunction, event reasoning, neuro-symbolic unification, and humour understanding (the highest level of cognition). All these suggest a new kind of Herbert A. Simon's scissors with two neural blades. SphNNs will tremendously enhance interdisciplinary collaborations to develop the two neural blades and realise deterministic neural reasoning and human-bounded rationality and elevate LLMs to reliable psychological AI. This work suggests that the non-zero radii of spheres are the missing components that prevent traditional deep-learning systems from reaching the realm of rational reasoning and cause LLMs to be trapped in the swamp of hallucination.
]]></description>
<dc:subject>neural-networks representation formal-logic ontology to-understand consider:classic-AI consider:member-of-networks rationality machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:336f8efa870b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formal-logic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ontology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:classic-AI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:member-of-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rationality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://machinelearning.apple.com/research/illusion-of-thinking">
    <title>The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity - Apple Machine Learning Research</title>
    <dc:date>2025-08-17T14:00:02+00:00</dc:date>
    <link>https://machinelearning.apple.com/research/illusion-of-thinking</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent generations of frontier language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their fundamental capabilities, scaling properties, and limitations remain insufficiently understood. Current evaluations primarily focus on established mathematical and coding benchmarks, emphasizing final answer accuracy. However, this evaluation paradigm often suffers from data contamination and does not provide insights into the reasoning traces’ structure and quality. In this work, we systematically investigate these gaps with the help of controllable puzzle environments that allow precise manipulation of compositional complexity while maintaining consistent logical structures. This setup enables the analysis of not only final answers but also the internal reasoning traces, offering insights into how LRMs “think”. Through extensive experimentation across diverse puzzles, we show that frontier LRMs face a complete accuracy collapse beyond certain complexities. Moreover, they exhibit a counter-intuitive scaling limit: their reasoning effort increases with problem complexity up to a point, then declines despite having an adequate token budget. By comparing LRMs with their standard LLM counterparts under equivalent inference compute, we identify three performance regimes: (1) low-complexity tasks where standard models surprisingly outperform LRMs, (2) medium-complexity tasks where additional thinking in LRMs demonstrates advantage, and (3) high-complexity tasks where both models experience complete collapse. We found that LRMs have limitations in exact computation: they fail to use explicit algorithms and reason inconsistently across puzzles. We also investigate the reasoning traces in more depth, studying the patterns of explored solutions and analyzing the models’ computational behavior, shedding light on their strengths, limitations, and ultimately raising crucial questions about their true reasoning capabilities.
]]></description>
<dc:subject>machine-learning Apple rather-interesting explanation artificial-intelligence-so-named validation verification to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b1d6c19d8952/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Apple"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence-so-named"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:verification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11047-025-10028-7">
    <title>Genetic programming policies for bin packing in the framework of deterministic Markov decision process | Natural Computing</title>
    <dc:date>2025-07-24T11:17:41+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11047-025-10028-7</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The Bin Packing Problem (BPP) is a well-known NP-hard problem with numerous real-world applications. This study focuses on minimizing waste and maximum lateness in a one-dimensional version of the BPP, which is particularly relevant in industrial contexts. The goal is to develop a constructive heuristic algorithm that can be adapted to various situations. We model the BPP as a Deterministic Markov Decision Process with discrete state and action spaces, where policies are represented by arithmetic expressions involving state variables. This approach allows for a clearer explanation of the decision process, in contrast to other methods like neural networks. To evolve these policies, we use Genetic Programming (GP). Trained on a set of BPP instances, the resulting policies are effective for solving new, unseen instances. In the experimental study, we explore different GP settings, including varying sets of symbols. The results reveal valuable insights about the importance of state variables, indicating that a smaller selection of them may yield the best results. The evolved policies are compared with an exact method from the literature, achieving similar outcomes but with significantly less computational time.

]]></description>
<dc:subject>operations-research packing genetic-programming rather-interesting deterministic-approximations approximation machine-learning to-write-about consider:heuristic-move</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:19868cd2a237/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:packing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deterministic-approximations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:heuristic-move"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2505.16217">
    <title>[2505.16217] Reward-Aware Proto-Representations in Reinforcement Learning</title>
    <dc:date>2025-05-27T22:45:41+00:00</dc:date>
    <link>https://arxiv.org/abs/2505.16217</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In recent years, the successor representation (SR) has attracted increasing attention in reinforcement learning (RL), and it has been used to address some of its key challenges, such as exploration, credit assignment, and generalization. The SR can be seen as representing the underlying credit assignment structure of the environment by implicitly encoding its induced transition dynamics. However, the SR is reward-agnostic. In this paper, we discuss a similar representation that also takes into account the reward dynamics of the problem. We study the default representation (DR), a recently proposed representation with limited theoretical (and empirical) analysis. Here, we lay some of the theoretical foundation underlying the DR in the tabular case by (1) deriving dynamic programming and (2) temporal-difference methods to learn the DR, (3) characterizing the basis for the vector space of the DR, and (4) formally extending the DR to the function approximation case through default features. Empirically, we analyze the benefits of the DR in many of the settings in which the SR has been applied, including (1) reward shaping, (2) option discovery, (3) exploration, and (4) transfer learning. Our results show that, compared to the SR, the DR gives rise to qualitatively different, reward-aware behaviour and quantitatively better performance in several settings.
]]></description>
<dc:subject>reinforcement-learning machine-learning metaheuristics to-understand consider:branching-processes consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e791c016042c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinforcement-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:branching-processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.pnas.org/doi/10.1073/pnas.0710743106">
    <title>Efficient computation of optimal actions | PNAS</title>
    <dc:date>2025-05-27T22:44:00+00:00</dc:date>
    <link>https://www.pnas.org/doi/10.1073/pnas.0710743106</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Optimal choice of actions is a fundamental problem relevant to fields as diverse as neuroscience, psychology, economics, computer science, and control engineering. Despite this broad relevance the abstract setting is similar: we have an agent choosing actions over time, an uncertain dynamical system whose state is affected by those actions, and a performance criterion that the agent seeks to optimize. Solving problems of this kind remains hard, in part, because of overly generic formulations. Here, we propose a more structured formulation that greatly simplifies the construction of optimal control laws in both discrete and continuous domains. An exhaustive search over actions is avoided and the problem becomes linear. This yields algorithms that outperform Dynamic Programming and Reinforcement Learning, and thereby solve traditional problems more efficiently. Our framework also enables computations that were not possible before: composing optimal control laws by mixing primitives, applying deterministic methods to stochastic systems, quantifying the benefits of error tolerance, and inferring goals from behavioral data via convex optimization. Development of a general class of easily solvable problems tends to accelerate progress—as linear systems theory has done, for example. Our framework may have similar impact in fields where optimal choice of actions is relevant.]]></description>
<dc:subject>machine-learning approximation algorithms rather-interesting computational-complexity to-understand mathematical-programming metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d4e94025ab87/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nature.com/articles/s41467-021-25123-3">
    <title>Linear reinforcement learning in planning, grid fields, and cognitive control | Nature Communications</title>
    <dc:date>2025-05-27T22:36:11+00:00</dc:date>
    <link>https://www.nature.com/articles/s41467-021-25123-3</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[It is thought that the brain’s judicious reuse of previous computation underlies our ability to plan flexibly, but also that inappropriate reuse gives rise to inflexibilities like habits and compulsion. Yet we lack a complete, realistic account of either. Building on control engineering, here we introduce a model for decision making in the brain that reuses a temporally abstracted map of future events to enable biologically-realistic, flexible choice at the expense of specific, quantifiable biases. It replaces the classic nonlinear, model-based optimization with a linear approximation that softly maximizes around (and is weakly biased toward) a default policy. This solution demonstrates connections between seemingly disparate phenomena across behavioral neuroscience, notably flexible replanning with biases and cognitive control. It also provides insight into how the brain can represent maps of long-distance contingencies stably and componentially, as in entorhinal response fields, and exploit them to guide choice even under changing goals.

]]></description>
<dc:subject>machine-learning reinforcement-learning to-understand planning exploration</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:84dde20fc4fa/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinforcement-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2504.17963">
    <title>[2504.17963] Mathematics of Continual Learning</title>
    <dc:date>2025-05-01T12:49:00+00:00</dc:date>
    <link>https://arxiv.org/abs/2504.17963</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Continual learning is an emerging subject in machine learning that aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks. Recently, many deep learning based approaches have been proposed for continual learning, however the mathematical foundations behind existing continual learning methods remain underdeveloped. On the other hand, adaptive filtering is a classic subject in signal processing with a rich history of mathematically principled methods. However, its role in understanding the foundations of continual learning has been underappreciated. In this tutorial, we review the basic principles behind both continual learning and adaptive filtering, and present a comparative analysis that highlights multiple connections between them. These connections allow us to enhance the mathematical foundations of continual learning based on existing results for adaptive filtering, extend adaptive filtering insights using existing continual learning methods, and discuss a few research directions for continual learning suggested by the historical developments in adaptive filtering.
]]></description>
<dc:subject>machine-learning continual-learning optimization memory rather-interesting to-understand to-write-about consider:symbolic-regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:641d7a964c27/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:continual-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:memory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nature.com/articles/s41467-025-59288-y">
    <title>Interactive symbolic regression with co-design mechanism through offline reinforcement learning | Nature Communications</title>
    <dc:date>2025-05-01T12:44:31+00:00</dc:date>
    <link>https://www.nature.com/articles/s41467-025-59288-y</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Symbolic Regression holds great potential for uncovering underlying mathematical and physical relationships from observed data. However, the vast combinatorial space of possible expressions poses significant challenges for previous online search methods and pre-trained transformer models, which mostly do not consider the integration of domain experts’ prior knowledge. To address these challenges, we propose the Symbolic Q-network, an advanced interactive framework for large-scale symbolic regression. Unlike previous transformer-based SR approaches, Symbolic Q-network leverages reinforcement learning without relying on a transformer-based decoder. Furthermore, we propose a co-design mechanism, where the Symbolic Q-network facilitates effective interaction with domain experts at any stage of the equation discovery process. Our extensive experiments demonstrate Sym-Q performs comparably to existing pretrained models across multiple benchmarks. Furthermore, our experiments on real-world cases demonstrate that the interactive co-design mechanism significantly enhances Symbolic Q-network’s performance, achieving greater performance gains than standard autoregressive models.

]]></description>
<dc:subject>symbolic-regression models-and-modes machine-learning rather-interesting reinvented-wheels to-understand metaheuristics reinforcement-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c682cbd2e528/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinvented-wheels"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinforcement-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2210.02580">
    <title>[2210.02580] Functional Labeled Optimal Partitioning</title>
    <dc:date>2025-04-17T14:14:29+00:00</dc:date>
    <link>https://arxiv.org/abs/2210.02580</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Peak detection is a problem in sequential data analysis that involves differentiating regions with higher counts (peaks) from regions with lower counts (background noise).
It is crucial to correctly predict areas that deviate from the background noise, in both the train and test sets of labels.
Dynamic programming changepoint algorithms have been proposed to solve the peak detection problem by constraining the mean to alternatively increase and then decrease.
The current constrained changepoint algorithms only create predictions on the test set, while completely ignoring the train set.
Changepoint algorithms that are both accurate when fitting the train set, and make predictions on the test set, have been proposed but not in the context of peak detection models.
We propose to resolve these issues by creating a new dynamic programming algorithm, FLOPART, that has zero train label errors, and is able to provide highly accurate predictions on the test set.
We provide an empirical analysis that shows FLOPART has a similar time complexity while being more accurate than the existing algorithms in terms of train and test label errors.
]]></description>
<dc:subject>machine-learning time-series algorithms rather-interesting data-analysis to-understand to-write-about consider:data-labeling consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:96c4dc95518d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:data-labeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2502.06871">
    <title>[2502.06871] FlavorDiffusion: Predicting Food Pairings and Chemical Interactions Using Diffusion Models</title>
    <dc:date>2025-04-16T22:29:20+00:00</dc:date>
    <link>https://arxiv.org/abs/2502.06871</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The study of food pairing has evolved beyond subjective expertise with the advent of machine learning. This paper presents FlavorDiffusion, a novel framework leveraging diffusion models to predict food-chemical interactions and ingredient pairings without relying on chromatography. By integrating graph-based embeddings, diffusion processes, and chemical property encoding, FlavorDiffusion addresses data imbalances and enhances clustering quality. Using a heterogeneous graph derived from datasets like Recipe1M and FlavorDB, our model demonstrates superior performance in reconstructing ingredient-ingredient relationships. The addition of a Chemical Structure Prediction (CSP) layer further refines the embedding space, achieving state-of-the-art NMI scores and enabling meaningful discovery of novel ingredient combinations. The proposed framework represents a significant step forward in computational gastronomy, offering scalable, interpretable, and chemically informed solutions for food science.
]]></description>
<dc:subject>aesthetics machine-learning cooking rather-interesting neural-networks generative-models to-write-about to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ac546774254f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aesthetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cooking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2502.08021">
    <title>[2502.08021] Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol</title>
    <dc:date>2025-04-16T22:26:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2502.08021</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Holdout validation and hyperparameter tuning from data is a long-standing problem in offline reinforcement learning (RL). A standard framework is to use off-policy evaluation (OPE) methods to evaluate and select the policies, but OPE either incurs exponential variance (e.g., importance sampling) or has hyperparameters on their own (e.g., FQE and model-based). In this work we focus on hyperparameter tuning for OPE itself, which is even more under-investigated. Concretely, we select among candidate value functions ("model-free") or dynamics ("model-based") to best assess the performance of a target policy. Our contributions are two fold. We develop: (1) new model-free and model-based selectors with theoretical guarantees, and (2) a new experimental protocol for empirically evaluating them. Compared to the model-free protocol in prior works, our new protocol allows for more stable generation of candidate value functions, better control of misspecification, and evaluation of model-free and model-based methods alike. We exemplify the protocol on a Gym environment, and find that our new model-free selector, LSTD-Tournament, demonstrates promising empirical performance.
]]></description>
<dc:subject>machine-learning validation training-vs-testing to-understand performance-measure hyperparameter-tuning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7fe943a0ebd9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:training-vs-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hyperparameter-tuning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2403.14139">
    <title>[2403.14139] Genetic Programming for Explainable Manifold Learning</title>
    <dc:date>2025-04-16T13:33:06+00:00</dc:date>
    <link>https://arxiv.org/abs/2403.14139</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Manifold learning techniques play a pivotal role in machine learning by revealing lower-dimensional embeddings within high-dimensional data, thus enhancing both the efficiency and interpretability of data analysis by transforming the data into a lower-dimensional representation. However, a notable challenge with current manifold learning methods is their lack of explicit functional mappings, crucial for explainability in many real-world applications. Genetic programming, known for its interpretable functional tree-based models, has emerged as a promising approach to address this challenge. Previous research leveraged multi-objective GP to balance manifold quality against embedding dimensionality, producing functional mappings across a range of embedding sizes. Yet, these mapping trees often became complex, hindering explainability. In response, in this paper, we introduce Genetic Programming for Explainable Manifold Learning (GP-EMaL), a novel approach that directly penalises tree complexity. Our new method is able to maintain high manifold quality while significantly enhancing explainability and also allows customisation of complexity measures, such as symmetry balancing, scaling, and node complexity, catering to diverse application needs. Our experimental analysis demonstrates that GP-EMaL is able to match the performance of the existing approach in most cases, while using simpler, smaller, and more interpretable tree structures. This advancement marks a significant step towards achieving interpretable manifold learning.
]]></description>
<dc:subject>machine-learning classification explanation representation to-write-about to-understand consider:why-trees?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3546abbc98a1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:why-trees?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2410.08304">
    <title>[2410.08304] Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers</title>
    <dc:date>2025-04-06T19:26:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2410.08304</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Despite their spectacular progress, language models still struggle on complex reasoning tasks, such as advanced mathematics. We consider a long-standing open problem in mathematics: discovering a Lyapunov function that ensures the global stability of a dynamical system. This problem has no known general solution, and algorithmic solvers only exist for some small polynomial systems. We propose a new method for generating synthetic training samples from random solutions, and show that sequence-to-sequence transformers trained on such datasets perform better than algorithmic solvers and humans on polynomial systems, and can discover new Lyapunov functions for non-polynomial systems.
]]></description>
<dc:subject>nonlinear-dynamics machine-learning reinventing-the-wheel symbolic-regression but-not-quite numerical-methods rather-interesting to-replicate consider:representation consider:performance-measures neural-networks transformer-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b39ac4a5b24e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinventing-the-wheel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:but-not-quite"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-replicate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:transformer-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2503.07811">
    <title>[2503.07811] A primer on optimal transport for causal inference with observational data</title>
    <dc:date>2025-04-05T22:00:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2503.07811</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The theory of optimal transportation has developed into a powerful and elegant framework for comparing probability distributions, with wide-ranging applications in all areas of science. The fundamental idea of analyzing probabilities by comparing their underlying state space naturally aligns with the core idea of causal inference, where understanding and quantifying counterfactual states is paramount. Despite this intuitive connection, explicit research at the intersection of optimal transport and causal inference is only beginning to develop. Yet, many foundational models in causal inference have implicitly relied on optimal transport principles for decades, without recognizing the underlying connection. Therefore, the goal of this review is to offer an introduction to the surprisingly deep existing connections between optimal transport and the identification of causal effects with observational data -- where optimal transport is not just a set of potential tools, but actually builds the foundation of model assumptions. As a result, this review is intended to unify the language and notation between different areas of statistics, mathematics, and econometrics, by pointing out these existing connections, and to explore novel problems and directions for future work in both areas derived from this realization.
]]></description>
<dc:subject>probability-theory optimal-transport causal-inference inference to-understand via:? modeling machine-learning numerical-methods</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:28573aa6a3a3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimal-transport"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:causal-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2312.12899">
    <title>[2312.12899] Collective dynamics and long-range order in thermal neuristor networks</title>
    <dc:date>2024-12-28T14:18:34+00:00</dc:date>
    <link>https://arxiv.org/abs/2312.12899</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the pursuit of scalable and energy-efficient neuromorphic devices, recent research has unveiled a novel category of spiking oscillators, termed "thermal neuristors." These devices function via thermal interactions among neighboring vanadium dioxide resistive memories, emulating biological neuronal behavior. Here, we show that the collective dynamical behavior of networks of these neurons showcases a rich phase structure, tunable by adjusting the thermal coupling and input voltage. Notably, we identify phases exhibiting long-range order that, however, does not arise from criticality, but rather from the time non-local response of the system. In addition, we show that these thermal neuristor arrays achieve high accuracy in image recognition and time series prediction through reservoir computing, without leveraging long-range order. Our findings highlight a crucial aspect of neuromorphic computing with possible implications on the functioning of the brain: criticality may not be necessary for the efficient performance of neuromorphic systems in certain computational tasks.
]]></description>
<dc:subject>reservoir-computing neural-networks nonlinear-dynamics machine-learning indistinguishable-from-magic rather-interesting to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bebdd58b8999/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indistinguishable-from-magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2411.12304">
    <title>[2411.12304] Emergence of Implicit World Models from Mortal Agents</title>
    <dc:date>2024-12-21T16:31:28+00:00</dc:date>
    <link>https://arxiv.org/abs/2411.12304</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the perspective of biological systems as understood by the mechanistic approach of theoretical biology and artificial life. From this perspective, we discuss the potential of homeostasis in particular as an open-ended objective for autonomous agents and as a general, integrative extrinsic motivation. We then discuss the possibility of implicitly acquiring a world model and active exploration through the internal dynamics of a network, and a hypothetical architecture for this, by combining meta-reinforcement learning, which assumes domain adaptation as a system that achieves robust homeostasis.
]]></description>
<dc:subject>autopoiesis open-ended-evolution artificial-life machine-learning algorithms to-read to-understand philosophy-of-engineering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:24353b147828/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:autopoiesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-ended-evolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.08348">
    <title>[2101.08348] Physical Reservoir Computing with Origami and its Application to Robotic Crawling</title>
    <dc:date>2024-11-01T19:07:32+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.08348</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A new paradigm called physical reservoir computing has recently emerged, where the nonlinear dynamics of high-dimensional and fixed physical systems are harnessed as a computational resource to achieve complex tasks. Via extensive simulations based on a dynamic truss-frame model, this study shows that an origami structure can perform as a dynamic reservoir with sufficient computing power to emulate high-order nonlinear systems, generate stable limit cycles, and modulate outputs according to dynamic inputs. This study also uncovers the linkages between the origami reservoir's physical designs and its computing power, offering a guideline to optimize the computing performance. Comprehensive parametric studies show that selecting optimal feedback crease distribution and fine-tuning the underlying origami folding designs are the most effective approach to improve computing performance. Furthermore, this study shows how origami's physical reservoir computing power can apply to soft robotic control problems by a case study of earthworm-like peristaltic crawling without traditional controllers. These results can pave the way for origami-based robots with embodied mechanical intelligence.
]]></description>
<dc:subject>reservoir-computing machine-learning distributed-processing collective-intelligence nonlinear-dynamics to-understand to-write-about to-simulate consider:where-is-the-thing?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dfc2a5b93f80/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distributed-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:where-is-the-thing?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.09780">
    <title>[2106.09780] Gradient-free optimization of chaotic acoustics with reservoir computing</title>
    <dc:date>2024-10-30T12:57:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.09780</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We develop a versatile optimization method, which finds the design parameters that minimize time-averaged acoustic cost functionals. The method is gradient-free, model-informed, and data-driven with reservoir computing based on echo state networks. First, we analyse the predictive capabilities of echo state networks both in the short- and long-time prediction of the dynamics. We find that both fully data-driven and model-informed architectures learn the chaotic acoustic dynamics, both time-accurately and statistically. Informing the training with a physical reduced-order model with one acoustic mode markedly improves the accuracy and robustness of the echo state networks, whilst keeping the computational cost low. Echo state networks offer accurate predictions of the long-time dynamics, which would be otherwise expensive by integrating the governing equations to evaluate the time-averaged quantity to optimize. Second, we couple echo state networks with a Bayesian technique to explore the design thermoacoustic parameter space. The computational method is minimally intrusive. Third, we find the set of flame parameters that minimize the time-averaged acoustic energy of chaotic oscillations, which are caused by the positive feedback with a heat source, such as a flame in gas turbines or rocket motors. These oscillations are known as thermoacoustic oscillations. The optimal set of flame parameters is found with the same accuracy as brute-force grid search, but with a convergence rate that is more than one order of magnitude faster. This work opens up new possibilities for non-intrusive ("hands-off") optimization of chaotic systems, in which the cost of generating data, for example from high-fidelity simulations and experiments, is high.
]]></description>
<dc:subject>reservoir-computing nonlinear-dynamics rather-interesting machine-learning to-understand to-write-about consider:symbolic-systems consider:language-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e8ec69648b00/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:language-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2304.13125">
    <title>[2304.13125] Estimating the master stability function from the time series of one oscillator via reservoir computing</title>
    <dc:date>2024-10-30T12:49:04+00:00</dc:date>
    <link>https://arxiv.org/abs/2304.13125</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The master stability function (MSF) yields the stability of the globally synchronized state of a network of identical oscillators in terms of the eigenvalues of the adjacency matrix. In order to compute the MSF, one must have an accurate model of an uncoupled oscillator, but often such a model does not exist. We present a reservoir computing technique for estimating the MSF given only the time series of a single, uncoupled oscillator. We demonstrate the generality of our technique by considering a variety of coupling configurations of networks consisting of Lorenz oscillators or H{é}non maps.
]]></description>
<dc:subject>nonlinear-dynamics reservoid-computing machine-learning remarkable-results to-understand to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b65825dec4e6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoid-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:remarkable-results"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2307.15092">
    <title>[2307.15092] A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning</title>
    <dc:date>2024-10-30T12:44:28+00:00</dc:date>
    <link>https://arxiv.org/abs/2307.15092</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into a non-linear dynamical system that maps low-dimensional inputs into a high-dimensional space. The model's rich dynamics, linear separability, and memory capacity then enable a simple linear readout to generate adequate responses for various applications. RC spans areas far beyond machine learning, since it has been shown that the complex dynamics can be realized in various physical hardware implementations and biological devices. This yields greater flexibility and shorter computation time. Moreover, the neuronal responses triggered by the model's dynamics shed light on understanding brain mechanisms that also exploit similar dynamical processes. While the literature on RC is vast and fragmented, here we conduct a unified review of RC's recent developments from machine learning to physics, biology, and neuroscience. We first review the early RC models, and then survey the state-of-the-art models and their applications. We further introduce studies on modeling the brain's mechanisms by RC. Finally, we offer new perspectives on RC development, including reservoir design, coding frameworks unification, physical RC implementations, and interaction between RC, cognitive neuroscience and evolution.
]]></description>
<dc:subject>nonlinear-dynamics reservoir-computing neural-networks machine-learning biologically-inspired to-understand rather-interesting to-write-about review</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f3ddd77750a4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biologically-inspired"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2401.09501">
    <title>[2401.09501] Reservoir computing with logistic map</title>
    <dc:date>2024-10-30T12:42:18+00:00</dc:date>
    <link>https://arxiv.org/abs/2401.09501</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent studies on reservoir computing essentially involve a high dimensional dynamical system as the reservoir, which transforms and stores the input as a higher dimensional state, for temporal and nontemporal data processing. We demonstrate here a method to predict temporal and nontemporal tasks by constructing virtual nodes as constituting a reservoir in reservoir computing using a nonlinear map, namely the logistic map, and a simple finite trigonometric series. We predict three nonlinear systems, namely Lorenz, Rossler, and Hindmarsh-Rose, for temporal tasks and a seventh order polynomial for nontemporal tasks with great accuracy. Also, the prediction is made in the presence of noise and found to closely agree with the target. Remarkably, the logistic map performs well and predicts close to the actual or target values. The low values of the root mean square error confirm the accuracy of this method in terms of efficiency. Our approach removes the necessity of continuous dynamical systems for constructing the reservoir in reservoir computing. Moreover, the accurate prediction for the three different nonlinear systems suggests that this method can be considered a general one and can be applied to predict many systems. Finally, we show that the method also accurately anticipates the time series of the all the three variable of Rossler system for the future (self prediction).
]]></description>
<dc:subject>reservoid-computing nonlinear-dynamics neural-networks rather-interesting to-write-about to-simulate machine-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c4b5225f808c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoid-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2403.16933">
    <title>[2403.16933] Backpropagation through space, time, and the brain</title>
    <dc:date>2024-10-30T12:39:59+00:00</dc:date>
    <link>https://arxiv.org/abs/2403.16933</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[How physical networks of neurons, bound by spatio-temporal locality constraints, can perform efficient credit assignment, remains, to a large extent, an open question. In machine learning, the answer is almost universally given by the error backpropagation algorithm, through both space and time. However, this algorithm is well-known to rely on biologically implausible assumptions, in particular with respect to spatio-temporal (non-)locality. Alternative forward-propagation models such as real-time recurrent learning only partially solve the locality problem, but only at the cost of scaling, due to prohibitive storage requirements.
We introduce Generalized Latent Equilibrium (GLE), a computational framework for fully local spatio-temporal credit assignment in physical, dynamical networks of neurons. We start by defining an energy based on neuron-local mismatches, from which we derive both neuronal dynamics via stationarity and parameter dynamics via gradient descent. The resulting dynamics can be interpreted as a real-time, biologically plausible approximation of backpropagation through space and time in deep cortical networks with continuous-time neuronal dynamics and continuously active, local synaptic plasticity. In particular, GLE exploits the morphology of dendritic trees to enable more complex information storage and processing in single neurons, as well as the ability of biological neurons to phase-shift their output rate with respect to their membrane potential, which is essential in both directions of information propagation. For the forward computation, it enables the mapping of time-continuous inputs to neuronal space, effectively performing a spatio-temporal convolution. For the backward computation, it permits the temporal inversion of feedback signals, which consequently approximate the adjoint variables necessary for useful parameter updates.]]></description>
<dc:subject>neural-networks backpropagation machine-learning yes-but-what-actually-happens rather-interesting nonlinear-dynamics systems-thinking locality biological-engineering to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8f8d06d46c7d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:backpropagation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:yes-but-what-actually-happens"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-thinking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:locality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biological-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2404.05259">
    <title>[2404.05259] Cellular automata, many-valued logic, and deep neural networks</title>
    <dc:date>2024-10-30T12:32:39+00:00</dc:date>
    <link>https://arxiv.org/abs/2404.05259</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We develop a theory characterizing the fundamental capability of deep neural networks to learn, from evolution traces, the logical rules governing the behavior of cellular automata (CA). This is accomplished by first establishing a novel connection between CA and Lukasiewicz propositional logic. While binary CA have been known for decades to essentially perform operations in Boolean logic, no such relationship exists for general CA. We demonstrate that many-valued (MV) logic, specifically Lukasiewicz propositional logic, constitutes a suitable language for characterizing general CA as logical machines. This is done by interpolating CA transition functions to continuous piecewise linear functions, which, by virtue of the McNaughton theorem, yield formulae in MV logic characterizing the CA. Recognizing that deep rectified linear unit (ReLU) networks realize continuous piecewise linear functions, it follows that these formulae are naturally extracted from CA evolution traces by deep ReLU networks. A corresponding algorithm together with a software implementation is provided. Finally, we show that the dynamical behavior of CA can be realized by recurrent neural networks.
]]></description>
<dc:subject>neural-networks cellular-automata learning-by-watching recurrent-networks nonlinear-dynamics approximation machine-learning to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:39d241f4a9a0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recurrent-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2205.08954">
    <title>[2205.08954] One-way Explainability Isn't The Message</title>
    <dc:date>2024-10-13T22:14:58+00:00</dc:date>
    <link>https://arxiv.org/abs/2205.08954</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent engineering developments in specialised computational hardware, data-acquisition and storage technology have seen the emergence of Machine Learning (ML) as a powerful form of data analysis with widespread applicability beyond its historical roots in the design of autonomous agents. However -- possibly because of its origins in the development of agents capable of self-discovery -- relatively little attention has been paid to the interaction between people and ML. In this paper we are concerned with the use of ML in automated or semi-automated tools that assist one or more human decision makers. We argue that requirements on both human and machine in this context are significantly different to the use of ML either as part of autonomous agents for self-discovery or as part statistical data analysis. Our principal position is that the design of such human-machine systems should be driven by repeated, two-way intelligibility of information rather than one-way explainability of the ML-system's recommendations. Iterated rounds of intelligible information exchange, we think, will characterise the kinds of collaboration that will be needed to understand complex phenomena for which neither man or machine have complete answers. We propose operational principles -- we call them Intelligibility Axioms -- to guide the design of a collaborative decision-support system. The principles are concerned with: (a) what it means for information provided by the human to be intelligible to the ML system; and (b) what it means for an explanation provided by an ML system to be intelligible to a human. Using examples from the literature on the use of ML for drug-design and in medicine, we demonstrate cases where the conditions of the axioms are met. We describe some additional requirements needed for the design of a truly collaborative decision-support system.
]]></description>
<dc:subject>machine-learning interpretability define-your-terms rather-interesting the-oracle-is-always-correct-you-just-aren't-holding-it-right to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0478938f44cb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-oracle-is-always-correct-you-just-aren't-holding-it-right"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.mdpi.com/2071-1050/11/7/1991">
    <title>Optimization of Concrete Mixture Design Using Adaptive Surrogate Model</title>
    <dc:date>2024-09-23T20:23:40+00:00</dc:date>
    <link>https://www.mdpi.com/2071-1050/11/7/1991</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The increase in urban construction in China has been accompanied by increasing concrete output, which has reached 2250 million m3 in recent years, ranked as the highest in the world. Consequentially, its environmental burden is significant in terms of resource use and carbon emissions. An adaptive surrogate model based on an extended radial basis function and adaptive sampling method was used to optimize the design of a concrete mixture in order to reduce its CO2 emissions and cost. The adaptive sampling method based on the multi-island genetic algorithm was adopted in order to improve the adaptive capability and accuracy of the surrogate model by selecting the proper sample size and ensuring uniform distribution of the sample points in the designed space. Three types of concrete with different strength, that is, C70, C40 and C30, were optimized by controlling the amount of fly ash and phosphorous slag in the samples. The optimized results showed that fly ash and phosphorous slag have a significant influence on the CO2 emissions of concrete and optimized concrete’s cost, while CO2 emissions were less than that of the reference samples. Therefore, the optimal mixture is with great significance to reduce the carbon emission of concrete, which also has implications for decreasing the environmental burden of concrete. In this way, we can optimize concrete of different strength to reduce carbon dioxide emission.
]]></description>
<dc:subject>experimental-design adaptive-experiment sampling machine-learning evolutionary-algorithms rather-interesting consider:resampling?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6baa85fab9ab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experimental-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adaptive-experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:resampling?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2310.10692">
    <title>[2310.10692] ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models</title>
    <dc:date>2024-09-21T14:05:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2310.10692</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The ability to invent novel and interesting problems is a remarkable feature of human intelligence that drives innovation, art, and science. We propose a method that aims to automate this process by harnessing the power of state-of-the-art generative models to produce a diversity of challenging yet solvable problems, here in the context of Python programming puzzles. Inspired by the intrinsically motivated literature, Autotelic CodE Search (ACES) jointly optimizes for the diversity and difficulty of generated problems. We represent problems in a space of LLM-generated semantic descriptors describing the programming skills required to solve them (e.g. string manipulation, dynamic programming, etc.) and measure their difficulty empirically as a linearly decreasing function of the success rate of Llama-3-70B, a state-of-the-art LLM problem solver. ACES iteratively prompts a large language model to generate difficult problems achieving a diversity of target semantic descriptors (goal-directed exploration) using previously generated problems as in-context examples. ACES generates problems that are more diverse and more challenging than problems produced by baseline methods and three times more challenging than problems found in existing Python programming benchmarks on average across 11 state-of-the-art code LLMs.
]]></description>
<dc:subject>machine-learning mathematical-recreations natural-language-processing generative-models rather-interesting to-write-about consider:genetic-programming consider:performance-measures consider:ludics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4444dfd877c3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:ludics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2406.11741">
    <title>[2406.11741] Transcendence: Generative Models Can Outperform The Experts That Train Them</title>
    <dc:date>2024-09-19T15:49:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2406.11741</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial model to outperform the humans on their original objectives. In this work, we study the phenomenon of transcendence: when a generative model achieves capabilities that surpass the abilities of the experts generating its data. We demonstrate transcendence by training an autoregressive transformer to play chess from game transcripts, and show that the trained model can sometimes achieve better performance than all players in the dataset. We theoretically prove that transcendence can be enabled by low-temperature sampling, and rigorously assess this claim experimentally. Finally, we discuss other sources of transcendence, laying the groundwork for future investigation of this phenomenon in a broader setting.
]]></description>
<dc:subject>neural-networks machine-learning learning-by-watching rather-interesting generative-models to-understand visualization purdy-pitchers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:12a6f4f11b23/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:purdy-pitchers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2409.05746">
    <title>[2409.05746] LLMs Will Always Hallucinate, and We Need to Live With This</title>
    <dc:date>2024-09-19T15:37:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2409.05746</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[As Large Language Models become more ubiquitous across domains, it becomes important to examine their inherent limitations critically. This work argues that hallucinations in language models are not just occasional errors but an inevitable feature of these systems. We demonstrate that hallucinations stem from the fundamental mathematical and logical structure of LLMs. It is, therefore, impossible to eliminate them through architectural improvements, dataset enhancements, or fact-checking mechanisms. Our analysis draws on computational theory and Godel's First Incompleteness Theorem, which references the undecidability of problems like the Halting, Emptiness, and Acceptance Problems. We demonstrate that every stage of the LLM process-from training data compilation to fact retrieval, intent classification, and text generation-will have a non-zero probability of producing hallucinations. This work introduces the concept of Structural Hallucination as an intrinsic nature of these systems. By establishing the mathematical certainty of hallucinations, we challenge the prevailing notion that they can be fully mitigated.
]]></description>
<dc:subject>machine-learning neural-networks hallucination performance-measure rather-interesting statistics philosophy-of-engineering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ec90a32de8c2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hallucination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2404.07150">
    <title>[2404.07150] Adaptive behavior with stable synapses</title>
    <dc:date>2024-08-17T21:57:35+00:00</dc:date>
    <link>https://arxiv.org/abs/2404.07150</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Behavioral changes in animals and humans, as a consequence of an error or a verbal instruction, can be extremely rapid. Improvement in behavioral performances are usually associated in machine learning and reinforcement learning to synaptic plasticity, and, in general, to changes and optimization of network parameters. However, such rapid changes are not coherent with the timescales of synaptic plasticity, suggesting that the mechanism responsible for that could be a dynamical network reconfiguration. In the last few years, similar capabilities have been observed in transformers, foundational architecture in the field of machine learning that are widely used in applications such as natural language and image processing. Transformers are capable of in-context learning, the ability to adapt and acquire new information dynamically within the context of the task or environment they are currently engaged in, without the need for significant changes to their underlying parameters. Building upon the notion of something unique within transformers enabling the emergence of this property, we claim that it could also be supported by input segregation and dendritic amplification, features extensively observed in biological networks. We propose an architecture composed of gain-modulated recurrent networks that excels at in-context learning, showing abilities inaccessible to standard networks.
]]></description>
<dc:subject>machine-learning recurrent-networks nonlinear-dynamics reservoir-computing to-understand neural-networks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0a416785cb98/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recurrent-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2309.03651">
    <title>[2309.03651] Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments</title>
    <dc:date>2024-08-14T20:27:00+00:00</dc:date>
    <link>https://arxiv.org/abs/2309.03651</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding the interactions of agents trained with deep reinforcement learning is crucial for deploying agents in games or the real world. In the former, unreasonable actions confuse players. In the latter, that effect is even more significant, as unexpected behavior cause accidents with potentially grave and long-lasting consequences for the involved individuals. In this work, we propose using program synthesis to imitate reinforcement learning policies after seeing a trajectory of the action sequence. Programs have the advantage that they are inherently interpretable and verifiable for correctness. We adapt the state-of-the-art program synthesis system DreamCoder for learning concepts in grid-based environments, specifically, a navigation task and two miniature versions of Atari games, Space Invaders and Asterix. By inspecting the generated libraries, we can make inferences about the concepts the black-box agent has learned and better understand the agent's behavior. We achieve the same by visualizing the agent's decision-making process for the imitated sequences. We evaluate our approach with different types of program synthesizers based on a search-only method, a neural-guided search, and a language model fine-tuned on code.
]]></description>
<dc:subject>machine-learning reinforcement-learning mazes-and-agents rather-interesting metaheuristics to-write-about consider:objectives interpretability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:308e14a91323/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinforcement-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mazes-and-agents"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:objectives"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2204.11041">
    <title>[2204.11041] Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection</title>
    <dc:date>2024-08-08T18:33:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2204.11041</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Out-of-distribution (OOD) detection is essential to handle the distribution shifts between training and test scenarios. For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution. In this paper, we propose a deep generative models (DGM) based transferable OOD detection method, which is unnecessary to retrain on a new ID dataset. We design an image erasing strategy to equip exclusive conditional entropy distribution for each ID dataset, which determines the discrepancy of DGM's posteriori ucertainty distribution on different ID datasets. Owing to the powerful representation capacity of convolutional neural networks, the proposed model trained on complex dataset can capture the above discrepancy between ID datasets without retraining and thus achieve transferable OOD detection. We validate the proposed method on five datasets and verity that ours achieves comparable performance to the state-of-the-art group based OOD detection methods that need to be retrained to deploy on new ID datasets. Our code is available at this https URL.
]]></description>
<dc:subject>machine-learning multitask-learning rather-interesting neural-networks image-processing forgetting to-understand consider:symbolic-regression anomaly-detection noise</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:23f2cee91736/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multitask-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:forgetting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anomaly-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:noise"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2109.04175">
    <title>[2109.04175] Safe, Deterministic Trajectory Planning for Unstructured and Partially Occluded Environments</title>
    <dc:date>2024-08-08T13:31:43+00:00</dc:date>
    <link>https://arxiv.org/abs/2109.04175</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Ensuring safe behavior for automated vehicles in unregulated traffic areas poses a complex challenge for the industry. It is an open problem to provide scalable and certifiable solutions to this challenge. We derive a trajectory planner based on model predictive control which interoperates with a monitoring system for pedestrian safety based on cellular automata. The combined planner-monitor system is demonstrated on the example of a narrow indoor parking environment. The system features deterministic behavior, mitigating the immanent risk of black boxes and offering full certifiability. By using fundamental and conservative prediction models of pedestrians the monitor is able to determine a safe drivable area in the partially occluded and unstructured parking environment. The information is fed to the trajectory planner which ensures the vehicle remains in the safe drivable area at any time through constrained optimization. We show how the approach enables solving plenty of situations in tight parking garage scenarios. Even though conservative prediction models are applied, evaluations indicate a performant system for the tested low-speed navigation.
]]></description>
<dc:subject>operations-research machine-learning rather-interesting planning computational-geometry online-learning online-planning robotics death-machines</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5b45c9fa4c7a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robotics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:death-machines"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2304.10521">
    <title>[2304.10521] A class of mesh-free algorithms for some problems arising in finance and machine learning</title>
    <dc:date>2024-08-06T14:25:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2304.10521</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce a numerical methodology, referred to as the transport-based mesh-free method, which allows us to deal with continuous, discrete, or statistical models in the same unified framework, and leads us to a broad class of numerical algorithms recently implemented in a Python library (namely, CodPy). Specifically, we propose a mesh-free discretization technique based on the theory of reproducing kernels and the theory of transport mappings, in a way that is reminiscent of Lagrangian methods in computational fluid dynamics. We introduce kernel-based discretizations of a variety of differential and discrete operators (gradient, divergence, Laplacian, Leray projection, extrapolation, interpolation, polar factorization). The proposed algorithms are nonlinear in nature and enjoy quantitative error estimates based on the notion of discrepancy error, which allows one to evaluate the relevance and accuracy of, both, the given data and the numerical solutions. Our strategy is relevant when a large number of degrees of freedom are present as is the case in mathematical finance and machine learning. We consider the Fokker-Planck-Kolmogorov system (relevant for problems arising in finance and material dynamics) and a class of neural networks based on support vector machines.
]]></description>
<dc:subject>numerical-methods python library kernel-methods calculus machine-learning to-understand to-learn consider:constant-fitting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0c3ef89e8233/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:kernel-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:calculus"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-learn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:constant-fitting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2405.06848">
    <title>[2405.06848] ISR: Invertible Symbolic Regression</title>
    <dc:date>2024-08-02T12:55:11+00:00</dc:date>
    <link>https://arxiv.org/abs/2405.06848</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce an Invertible Symbolic Regression (ISR) method. It is a machine learning technique that generates analytical relationships between inputs and outputs of a given dataset via invertible maps (or architectures). The proposed ISR method naturally combines the principles of Invertible Neural Networks (INNs) and Equation Learner (EQL), a neural network-based symbolic architecture for function learning. In particular, we transform the affine coupling blocks of INNs into a symbolic framework, resulting in an end-to-end differentiable symbolic invertible architecture that allows for efficient gradient-based learning. The proposed ISR framework also relies on sparsity promoting regularization, allowing the discovery of concise and interpretable invertible expressions. We show that ISR can serve as a (symbolic) normalizing flow for density estimation tasks. Furthermore, we highlight its practical applicability in solving inverse problems, including a benchmark inverse kinematics problem, and notably, a geoacoustic inversion problem in oceanography aimed at inferring posterior distributions of underlying seabed parameters from acoustic signals.
]]></description>
<dc:subject>symbolic-regression neural-networks machine-learning rather-interesting representation system-of-professions do-it-MIT-style to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:55871e2e6342/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:do-it-MIT-style"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.02705">
    <title>[2402.02705] Representation Surgery for Multi-Task Model Merging</title>
    <dc:date>2024-08-02T11:26:47+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.02705</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Multi-task learning (MTL) compresses the information from multiple tasks into a unified backbone to improve computational efficiency and generalization. Recent work directly merges multiple independently trained models to perform MTL instead of collecting their raw data for joint training, greatly expanding the application scenarios of MTL. However, by visualizing the representation distribution of existing model merging schemes, we find that the merged model often suffers from the dilemma of representation bias. That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL. In this paper, we propose a representation surgery solution called "Surgery" to reduce representation bias in the merged model. Specifically, Surgery is a lightweight task-specific module that takes the representation of the merged model as input and attempts to output the biases contained in the representation from the merged model. We then designed an unsupervised optimization objective that updates the Surgery module by minimizing the distance between the merged model's representation and the individual model's representation. Extensive experiments demonstrate significant MTL performance improvements when our Surgery module is applied to state-of-the-art (SOTA) model merging schemes.
]]></description>
<dc:subject>multitask-learning machine-learning rather-interesting generalization algorithms representation to-understand to-simulate consider:functional-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a37943ea4923/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multitask-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:functional-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2111.10722">
    <title>[2111.10722] A Deterministic Sampling Method via Maximum Mean Discrepancy Flow with Adaptive Kernel</title>
    <dc:date>2024-08-02T01:19:43+00:00</dc:date>
    <link>https://arxiv.org/abs/2111.10722</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a novel deterministic sampling method to approximate a target distribution ρ∗ by minimizing the kernel discrepancy, also known as the Maximum Mean Discrepancy (MMD). By employing the general \emph{energetic variational inference} framework (Wang et al., 2021), we convert the problem of minimizing MMD to solving a dynamic ODE system of the particles. We adopt the implicit Euler numerical scheme to solve the ODE systems. This leads to a proximal minimization problem in each iteration of updating the particles, which can be solved by optimization algorithms such as L-BFGS. The proposed method is named EVI-MMD. To overcome the long-existing issue of bandwidth selection of the Gaussian kernel, we propose a novel way to specify the bandwidth dynamically. Through comprehensive numerical studies, we have shown the proposed adaptive bandwidth significantly improves the EVI-MMD. We use the EVI-MMD algorithm to solve two types of sampling problems. In the first type, the target distribution is given by a fully specified density function. The second type is a "two-sample problem", where only training data are available. The EVI-MMD method is used as a generative learning model to generate new samples that follow the same distribution as the training data. With the recommended settings of the tuning parameters, we show that the proposed EVI-MMD method outperforms some existing methods for both types of problems.
]]></description>
<dc:subject>machine-learning discrepancy-theory approximation sampling really-very-interesting to-write-about consider:combinatorics consider:algorithmic-information-theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b9864fa33c22/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrepancy-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:really-very-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:algorithmic-information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2405.18029">
    <title>[2405.18029] Are Image Distributions Indistinguishable to Humans Indistinguishable to Classifiers?</title>
    <dc:date>2024-08-01T11:52:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2405.18029</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The ultimate goal of generative models is to characterize the data distribution perfectly. For image generation, common metrics of visual quality (e.g., FID), and the truthlikeness of generated images to the human eyes seem to suggest that we are close to achieving it. However, through distribution classification tasks, we find that, in the eyes of classifiers parameterized by neural networks, the strongest diffusion models are still far from this goal. Specifically, classifiers consistently and effortlessly distinguish between real and generated images in various settings. Further, we observe an intriguing discrepancy: classifiers can identify differences between diffusion models with similar performance (e.g., U-ViT-H vs. DiT-XL), but struggle to differentiate between the smallest and largest models in the same family (e.g., EDM2-XS vs. EDM2-XXL), whereas humans exhibit the opposite tendency. As an explanation, our comprehensive empirical study suggests that, unlike humans, classifiers tend to classify images through edge and high-frequency components. We believe that our methodology can serve as a probe to understand how generative models work and inspire further thought on how existing models can be improved and how the abuse of such models can be prevented.
]]></description>
<dc:subject>generative-art machine-learning image-processing rather-interesting who-watches-the-watchbeings? feature-selection</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:17ff7e674344/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:who-watches-the-watchbeings?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-selection"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.05482">
    <title>[2203.05482] Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time</title>
    <dc:date>2024-07-21T15:46:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.05482</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the remainder. In this paper, we revisit the second step of this procedure in the context of fine-tuning large pre-trained models, where fine-tuned models often appear to lie in a single low error basin. We show that averaging the weights of multiple models fine-tuned with different hyperparameter configurations often improves accuracy and robustness. Unlike a conventional ensemble, we may average many models without incurring any additional inference or memory costs -- we call the results "model soups." When fine-tuning large pre-trained models such as CLIP, ALIGN, and a ViT-G pre-trained on JFT, our soup recipe provides significant improvements over the best model in a hyperparameter sweep on ImageNet. The resulting ViT-G model, which attains 90.94% top-1 accuracy on ImageNet, achieved a new state of the art. Furthermore, we show that the model soup approach extends to multiple image classification and natural language processing tasks, improves out-of-distribution performance, and improves zero-shot performance on new downstream tasks. Finally, we analytically relate the performance similarity of weight-averaging and logit-ensembling to flatness of the loss and confidence of the predictions, and validate this relation empirically. Code is available at this https URL.
]]></description>
<dc:subject>machine-learning collective-behavior rather-interesting algorithms to-understand to-write-about constant-fitting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0e9d3e705931/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constant-fitting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2407.04491">
    <title>[2407.04491] Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data</title>
    <dc:date>2024-07-15T16:26:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2407.04491</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[For classification and regression on tabular data, the dominance of gradient-boosted decision trees (GBDTs) has recently been challenged by often much slower deep learning methods with extensive hyperparameter tuning. We address this discrepancy by introducing (a) RealMLP, an improved multilayer perceptron (MLP), and (b) improved default parameters for GBDTs and RealMLP. We tune RealMLP and the default parameters on a meta-train benchmark with 71 classification and 47 regression datasets and compare them to hyperparameter-optimized versions on a disjoint meta-test benchmark with 48 classification and 42 regression datasets, as well as the GBDT-friendly benchmark by Grinsztajn et al. (2022). Our benchmark results show that RealMLP offers a better time-accuracy tradeoff than other neural nets and is competitive with GBDTs. Moreover, a combination of RealMLP and GBDTs with improved default parameters can achieve excellent results on medium-sized tabular datasets (1K--500K samples) without hyperparameter tuning.
]]></description>
<dc:subject>machine-learning collective-intelligence performance-space-analysis neural-networks rather-interesting to-write-about consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:96a77215eae2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.08013">
    <title>[2107.08013] Machine learning of Kondo physics using variational autoencoders and symbolic regression</title>
    <dc:date>2024-07-10T13:41:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.08013</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We employ variational autoencoders to extract physical insight from a dataset of one-particle Anderson impurity model spectral functions. Autoencoders are trained to find a low-dimensional, latent space representation that faithfully characterizes each element of the training set, as measured by a reconstruction error. Variational autoencoders, a probabilistic generalization of standard autoencoders, further condition the learned latent space to promote highly interpretable features. In our study, we find that the learned latent variables strongly correlate with well known, but nontrivial, parameters that characterize emergent behaviors in the Anderson impurity model. In particular, one latent variable correlates with particle-hole asymmetry, while another is in near one-to-one correspondence with the Kondo temperature, a dynamically generated low-energy scale in the impurity model. Using symbolic regression, we model this variable as a function of the known bare physical input parameters and "rediscover" the non-perturbative formula for the Kondo temperature. The machine learning pipeline we develop suggests a general purpose approach which opens opportunities to discover new domain knowledge in other physical systems.
]]></description>
<dc:subject>materials-science learning-from-data genetic-programming symbolic-regression machine-learning rather-interesting clustering pattern-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:af6a41ae0e59/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:materials-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2310.02227">
    <title>[2310.02227] SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training</title>
    <dc:date>2024-07-03T10:07:18+00:00</dc:date>
    <link>https://arxiv.org/abs/2310.02227</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In an era where symbolic mathematical equations are indispensable for modeling complex natural phenomena, scientific inquiry often involves collecting observations and translating them into mathematical expressions. Recently, deep learning has emerged as a powerful tool for extracting insights from data. However, existing models typically specialize in either numeric or symbolic domains, and are usually trained in a supervised manner tailored to specific tasks. This approach neglects the substantial benefits that could arise from a task-agnostic multi-modal understanding between symbolic equations and their numeric counterparts. To bridge the gap, we introduce SNIP, a Symbolic-Numeric Integrated Pre-training model, which employs contrastive learning between symbolic and numeric domains, enhancing their mutual similarities in the embeddings. By performing latent space analysis, we observe that SNIP provides cross-domain insights into the representations, revealing that symbolic supervision enhances the embeddings of numeric data and vice versa. We evaluate SNIP across diverse tasks, including symbolic-to-numeric mathematical property prediction and numeric-to-symbolic equation discovery, commonly known as symbolic regression. Results show that SNIP effectively transfers to various tasks, consistently outperforming fully supervised baselines and competing strongly with established task-specific methods, especially in the low data regime scenarios where available data is limited. Code and model are available at: this https URL
]]></description>
<dc:subject>symbolic-regression when-you-have-a-hammer-everything-looks-like-a-neural machine-learning le-sigh</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d40f6c99ed6c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:when-you-have-a-hammer-everything-looks-like-a-neural"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:le-sigh"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2405.17514">
    <title>[2405.17514] AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning</title>
    <dc:date>2024-07-02T11:14:00+00:00</dc:date>
    <link>https://arxiv.org/abs/2405.17514</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[LambdaBeam is a state-of-the-art execution-guided algorithm for program synthesis that incorporates higher-order functions, lambda functions, and iterative loops into the Domain-Specific Language (DSL). LambdaBeam generates every program from the start. Yet, many program blocks or subprograms occur frequently in a given domain, e.g., loops to traverse a list. Thus, repeating programs can be used to enhance the synthesis algorithm. However, LambdaBeam fails to leverage this potential. For this purpose, we introduce AbstractBeam: A novel program synthesis framework that employs Library Learning to identify such program repetitions, integrates them into the DSL, and thus utilizes their potential to boost LambdaBeam's synthesis algorithm. Our experimental evaluations demonstrate that AbstractBeam significantly improves LambdaBeam's performance in the LambdaBeam integer list manipulation domain. Additionally, AbstractBeam's program generation is more efficient compared to LambdaBeam's synthesis. Finally, our findings indicate that Library Learning is effective in domains not specifically crafted to highlight its benefits.
]]></description>
<dc:subject>program-synthesis machine-learning learning-by-watching to-write-about consider:genetic-programming consider:DSL-design</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:680f09767a6d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:program-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:DSL-design"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2301.11919">
    <title>[2301.11919] Incorporating Background Knowledge in Symbolic Regression using a Computer Algebra System</title>
    <dc:date>2024-07-02T10:47:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2301.11919</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Symbolic Regression (SR) can generate interpretable, concise expressions that fit a given dataset, allowing for more human understanding of the structure than black-box approaches. The addition of background knowledge (in the form of symbolic mathematical constraints) allows for the generation of expressions that are meaningful with respect to theory while also being consistent with data. We specifically examine the addition of constraints to traditional genetic algorithm (GA) based SR (PySR) as well as a Markov-chain Monte Carlo (MCMC) based Bayesian SR architecture (Bayesian Machine Scientist), and apply these to rediscovering adsorption equations from experimental, historical datasets. We find that, while hard constraints prevent GA and MCMC SR from searching, soft constraints can lead to improved performance both in terms of search effectiveness and model meaningfulness, with computational costs increasing by about an order-of-magnitude. If the constraints do not correlate well with the dataset or expected models, they can hinder the search of expressions. We find Bayesian SR is better these constraints (as the Bayesian prior) than by modifying the fitness function in the GA
]]></description>
<dc:subject>symbolic-regression constraint-satisfaction machine-learning rather-interesting expertise to-write-about consider:stacks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2d8fb2148fb4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:expertise"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stacks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.04708">
    <title>[2202.04708] Active Learning Improves Performance on Symbolic RegressionTasks in StackGP</title>
    <dc:date>2024-07-01T20:28:35+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.04708</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we introduce an active learning method for symbolic regression using StackGP. The approach begins with a small number of data points for StackGP to model. To improve the model the system incrementally adds a data point such that the new point maximizes prediction uncertainty as measured by the model ensemble. Symbolic regression is re-run with the larger data set. This cycle continues until the system satisfies a termination criterion. We use the Feynman AI benchmark set of equations to examine the ability of our method to find appropriate models using fewer data points. The approach was found to successfully rediscover 72 of the 100 Feynman equations using as few data points as possible, and without use of domain expertise or data translation.
]]></description>
<dc:subject>symbolic-regression hey-I-know-this-guy genetic-programming horse-races stack-based-representations active-learning machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:971305a6cbcd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stack-based-representations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:active-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.04962">
    <title>[1808.04962] Recent Advances in Physical Reservoir Computing: A Review</title>
    <dc:date>2024-05-25T13:09:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.04962</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.
]]></description>
<dc:subject>reservoir-computing neural-networks machine-learning physics! bucket-brains rather-interesting to-write-about to-try consider:formal-logic-linear-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e2a880a81116/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics!"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bucket-brains"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:formal-logic-linear-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=HGsQrD6pPGM">
    <title>Next generation reservoir computer - Dan Gauthier - YouTube</title>
    <dc:date>2024-04-15T11:50:44+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=HGsQrD6pPGM</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data. Importantly, it requires very small training data sets, uses linear optimization, and thus requires minimal computing resources. However, the algorithm uses randomly sampled matrices to define the underlying recurrent neural network and has a multitude of metaparameters that must be optimized. Recent results demonstrate the equivalence of reservoir computing to nonlinear vector autoregression, which requires no random matrices, fewer metaparameters, and provides interpretable results. Here, we demonstrate that nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.
]]></description>
<dc:subject>reservoi-computing machine-learning yes-but nonlinear-mapping rather-interesting to-understand bring-me-a-bucket</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:800c6da3cb69/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoi-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:yes-but"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-mapping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bring-me-a-bucket"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2208.14567">
    <title>[2208.14567] LINKS: A dataset of a hundred million planar linkage mechanisms for data-driven kinematic design</title>
    <dc:date>2024-04-12T21:56:57+00:00</dc:date>
    <link>https://arxiv.org/abs/2208.14567</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we introduce LINKS, a dataset of 100 million one degree of freedom planar linkage mechanisms and 1.1 billion coupler curves, which is more than 1000 times larger than any existing database of planar mechanisms and is not limited to specific kinds of mechanisms such as four-bars, six-bars, \etc which are typically what most databases include. LINKS is made up of various components including 100 million mechanisms, the simulation data for each mechanism, normalized paths generated by each mechanism, a curated set of paths, the code used to generate the data and simulate mechanisms, and a live web demo for interactive design of linkage mechanisms. The curated paths are provided as a measure for removing biases in the paths generated by mechanisms that enable a more even design space representation. In this paper, we discuss the details of how we can generate such a large dataset and how we can overcome major issues with such scales. To be able to generate such a large dataset we introduce a new operator to generate 1-DOF mechanism topologies, furthermore, we take many steps to speed up slow simulations of mechanisms by vectorizing our simulations and parallelizing our simulator on a large number of threads, which leads to a simulation 800 times faster than the simple simulation algorithm. This is necessary given on average, 1 out of 500 candidates that are generated are valid~(and all must be simulated to determine their validity), which means billions of simulations must be performed for the generation of this dataset. Then we demonstrate the depth of our dataset through a bi-directional chamfer distance-based shape retrieval study where we show how our dataset can be used directly to find mechanisms that can trace paths very close to desired target paths.
]]></description>
<dc:subject>kinematics linkage planar-mechanisms enumeration machine-learning rather-interesting prototype-based-learning to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:33ff658237fc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:kinematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:linkage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planar-mechanisms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:enumeration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prototype-based-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2210.14707">
    <title>[2210.14707] Is Out-of-Distribution Detection Learnable?</title>
    <dc:date>2023-10-10T10:29:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2210.14707</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms. To study the generalization of OOD detection, in this paper, we investigate the probably approximately correct (PAC) learning theory of OOD detection, which is proposed by researchers as an open problem. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we also offer theoretical supports for several representative OOD detection works based on our OOD theory.
]]></description>
<dc:subject>machine-learning rather-interesting probability-theory to-write-about to-understand consider:online-learning consider:triggers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a98225133e02/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:triggers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2209.14440">
    <title>[2209.14440] GeONet: a neural operator for learning the Wasserstein geodesic</title>
    <dc:date>2023-09-30T12:46:11+00:00</dc:date>
    <link>https://arxiv.org/abs/2209.14440</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Optimal transport (OT) offers a versatile framework to compare complex data distributions in a geometrically meaningful way. Traditional methods for computing the Wasserstein distance and geodesic between probability measures require mesh-dependent domain discretization and suffer from the curse-of-dimensionality. We present GeONet, a mesh-invariant deep neural operator network that learns the non-linear mapping from the input pair of initial and terminal distributions to the Wasserstein geodesic connecting the two endpoint distributions. In the offline training stage, GeONet learns the saddle point optimality conditions for the dynamic formulation of the OT problem in the primal and dual spaces that are characterized by a coupled PDE system. The subsequent inference stage is instantaneous and can be deployed for real-time predictions in the online learning setting. We demonstrate that GeONet achieves comparable testing accuracy to the standard OT solvers on simulation examples and the MNIST dataset with considerably reduced inference-stage computational cost by orders of magnitude.
]]></description>
<dc:subject>machine-learning probability-theory rather-interesting metrics distance numerical-methods approximation neural-networks consider:looking-to-see consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2550a216a21d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.04739">
    <title>[2206.04739] I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs</title>
    <dc:date>2023-08-06T12:53:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.04739</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization. Recently, contrastive learning has emerged as a successful unsupervised representation learning method. Despite the prosperous development of contrastive learning in other domains, contrastive learning on hypergraphs remains little explored. In this paper, we propose TriCL (Tri-directional Contrastive Learning), a general framework for contrastive learning on hypergraphs. Its main idea is tri-directional contrast, and specifically, it aims to maximize in two augmented views the agreement (a) between the same node, (b) between the same group of nodes, and (c) between each group and its members. Together with simple but surprisingly effective data augmentation and negative sampling schemes, these three forms of contrast enable TriCL to capture both microscopic and mesoscopic structural information in node embeddings. Our extensive experiments using 13 baseline approaches, five datasets, and two tasks demonstrate the effectiveness of TriCL, and most noticeably, TriCL consistently outperforms not just unsupervised competitors but also (semi-)supervised competitors mostly by significant margins for node classification. The code and datasets are available at this https URL.
]]></description>
<dc:subject>collective-intelligence machine-learning hypergraphs rather-interesting coevolution metaheuristics consider:population-structures contrastive-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6caae70677fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coevolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:population-structures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:contrastive-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.09179">
    <title>[2202.09179] Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images</title>
    <dc:date>2023-02-09T12:39:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.09179</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction. However, common dimensionality reduction methods do not include spatial information present in images, such as local texture features, into the construction of low-dimensional embeddings. Consequently, exploration of such data is typically split into a step focusing on the attribute space followed by a step focusing on spatial information, or vice versa. In this paper, we present a method for incorporating spatial neighborhood information into distance-based dimensionality reduction methods, such as t-Distributed Stochastic Neighbor Embedding (t-SNE). We achieve this by modifying the distance measure between high-dimensional attribute vectors associated with each pixel such that it takes the pixel's spatial neighborhood into account. Based on a classification of different methods for comparing image patches, we explore a number of different approaches. We compare these approaches from a theoretical and experimental point of view. Finally, we illustrate the value of the proposed methods by qualitative and quantitative evaluation on synthetic data and two real-world use cases.
]]></description>
<dc:subject>image-processing representation rather-interesting patterns machine-learning clustering to-write-about to-visualize consider:nonlocality</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8c6ec7deec3b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:patterns"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonlocality"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.10541">
    <title>[2105.10541] Addressing the Multiplicity of Solutions in Optical Lens Design as a Niching Evolutionary Algorithms Computational Challenge</title>
    <dc:date>2023-02-07T12:58:57+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.10541</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Optimal Lens Design constitutes a fundamental, long-standing real-world optimization challenge. Potentially large number of optima, rich variety of critical points, as well as solid understanding of certain optimal designs per simple problem instances, provide altogether the motivation to address it as a niching challenge. This study applies established Niching-CMA-ES heuristic to tackle this design problem (6-dimensional Cooke triplet) in a simulation-based fashion. The outcome of employing Niching-CMA-ES `out-of-the-box' proves successful, and yet it performs best when assisted by a local searcher which accurately drives the search into optima. The obtained search-points are corroborated based upon concrete knowledge of this problem-instance, accompanied by gradient and Hessian calculations for validation. We extensively report on this computational campaign, which overall resulted in (i) the location of 19 out of 21 known minima within a single run, (ii) the discovery of 540 new optima. These are new minima similar in shape to 21 theoretical solutions, but some of them have better merit function value (unknown heretofore), (iii) the identification of numerous infeasibility pockets throughout the domain (also unknown heretofore). We conclude that niching mechanism is well-suited to address this problem domain, and hypothesize on the apparent multidimensional structures formed by the attained new solutions.
]]></description>
<dc:subject>evolutionary-algorithms multiobjective-optimization machine-learning engineering-design rather-interesting performance-measure to-simulate consider:visualization optics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:461cdf4aac8d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2205.09438">
    <title>[2205.09438] Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?</title>
    <dc:date>2022-10-04T10:50:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2205.09438</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Finding accurate solutions to the Schrödinger equation is the key unsolved challenge of computational chemistry. Given its importance for the development of new chemical compounds, decades of research have been dedicated to this problem, but due to the large dimensionality even the best available methods do not yet reach the desired accuracy. Recently the combination of deep learning with Monte Carlo methods has emerged as a promising way to obtain highly accurate energies and moderate scaling of computational cost. In this paper we significantly contribute towards this goal by introducing a novel deep-learning architecture that achieves 40-70% lower energy error at 8x lower computational cost compared to previous approaches. Using our method we establish a new benchmark by calculating the most accurate variational ground state energies ever published for a number of different atoms and molecules. We systematically break down and measure our improvements, focusing in particular on the effect of increasing physical prior knowledge. We surprisingly find that increasing the prior knowledge given to the architecture can actually decrease accuracy.
]]></description>
<dc:subject>physics! quantums symbolic-regression proxy-models rather-interesting neural-networks machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6b6396cea45e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics!"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quantums"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:proxy-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1712.07897">
    <title>[1712.07897] Non-convex Optimization for Machine Learning</title>
    <dc:date>2022-09-05T12:11:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1712.07897</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A vast majority of machine learning algorithms train their models and perform inference by solving optimization problems. In order to capture the learning and prediction problems accurately, structural constraints such as sparsity or low rank are frequently imposed or else the objective itself is designed to be a non-convex function. This is especially true of algorithms that operate in high-dimensional spaces or that train non-linear models such as tensor models and deep networks. 
The freedom to express the learning problem as a non-convex optimization problem gives immense modeling power to the algorithm designer, but often such problems are NP-hard to solve. A popular workaround to this has been to relax non-convex problems to convex ones and use traditional methods to solve the (convex) relaxed optimization problems. However this approach may be lossy and nevertheless presents significant challenges for large scale optimization. 
On the other hand, direct approaches to non-convex optimization have met with resounding success in several domains and remain the methods of choice for the practitioner, as they frequently outperform relaxation-based techniques - popular heuristics include projected gradient descent and alternating minimization. However, these are often poorly understood in terms of their convergence and other properties. 
This monograph presents a selection of recent advances that bridge a long-standing gap in our understanding of these heuristics. The monograph will lead the reader through several widely used non-convex optimization techniques, as well as applications thereof. The goal of this monograph is to both, introduce the rich literature in this area, as well as equip the reader with the tools and techniques needed to analyze these simple procedures for non-convex problems.
]]></description>
<dc:subject>via:cshalizi operations-research machine-learning optimization algorithms nonconvex-problems review numerical-methods</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0d6682608a03/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonconvex-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.00666">
    <title>[2202.00666] Typical Decoding for Natural Language Generation</title>
    <dc:date>2022-07-10T11:26:07+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.00666</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Despite achieving incredibly low perplexities on myriad natural language corpora, today's language models still often underperform when used to generate text. This dichotomy has puzzled the language generation community for the last few years. In this work, we posit that the abstraction of natural language as a communication channel (à la Shannon, 1948) can provide new insights into the behaviors of probabilistic language generators, e.g., why high-probability texts can be dull or repetitive. Humans use language as a means of communicating information, and do so in a simultaneously efficient and error-minimizing manner; they choose each word in a string with this (perhaps subconscious) goal in mind. We propose that generation from probabilistic models should mimic this behavior. Rather than always choosing words from the high-probability region of the distribution--which have a low Shannon information content--we sample from the set of words with information content close to the conditional entropy of our model, i.e., close to the expected information content. This decision criterion can be realized through a simple and efficient implementation, which we call typical sampling. Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, typical sampling offers competitive performance in terms of quality while consistently reducing the number of degenerate repetitions.
]]></description>
<dc:subject>generative-models natural-language-processing pragmatics rather-interesting multiobjective-optimization heuristics machine-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fd18d1632bfc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pragmatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>