<?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/2504.11406"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.04298"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2407.03510"/>
	<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/s41467-025-59288-y"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/s41586-023-06600-9?ref=longnow.org"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2109.13103"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2309.03651"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2303.06524v4"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2212.06313"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2304.07089"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.04739"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2207.09618"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2008.06530"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.07957"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.04672"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2009.00363"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.08691"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.09563"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.05236"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.06339"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.02262"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2005.05955"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.00205"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.02334"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.05628"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1806.09935"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.09813"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.05755"/>
	<rdf:li rdf:resource="https://openreview.net/forum?id=S1sqHMZCb"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.09670"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.05045"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.00937"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.04966"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.01218"/>
	<rdf:li rdf:resource="http://htsang.wikidot.com/research"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/0706.1754"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1902.04692"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.07617"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.08226"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.01672"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1905.03427"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.07983"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.01312"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.03548"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1806.03455"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.03495"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.08584"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.05850"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1707.04016"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.02873"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.04491"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1809.07406"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.00045"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.02851"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.03600"/>
	<rdf:li rdf:resource="https://www.degruyter.com/view/j/pjbr.2013.4.issue-1/pjbr-2013-0003/pjbr-2013-0003.xml"/>
	<rdf:li rdf:resource="https://www.sciencedirect.com/science/article/abs/pii/S0377221710006211"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.01076"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.08835"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.05915"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1708.01625"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1504.04909"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1708.00214"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.10201"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1706.04119"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.00853"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.07929"/>
      </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/2504.11406">
    <title>[2504.11406] Multi-level Cellular Automata for FLIM networks</title>
    <dc:date>2026-05-25T12:01:55+00:00</dc:date>
    <link>https://arxiv.org/abs/2504.11406</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The necessity of abundant annotated data and complex network architectures presents a significant challenge in deep-learning Salient Object Detection (deep SOD) and across the broader deep-learning landscape. This challenge is particularly acute in medical applications in developing countries with limited computational resources. Combining modern and classical techniques offers a path to maintaining competitive performance while enabling practical applications. Feature Learning from Image Markers (FLIM) methodology empowers experts to design convolutional encoders through user-drawn markers, with filters learned directly from these annotations. Recent findings demonstrate that coupling a FLIM encoder with an adaptive decoder creates a flyweight network suitable for SOD, requiring significantly fewer parameters than lightweight models and eliminating the need for backpropagation. Cellular Automata (CA) methods have proven successful in data-scarce scenarios but require proper initialization -- typically through user input, priors, or randomness. We propose a practical intersection of these approaches: using FLIM networks to initialize CA states with expert knowledge without requiring user interaction for each image. By decoding features from each level of a FLIM network, we can initialize multiple CAs simultaneously, creating a multi-level framework. Our method leverages the hierarchical knowledge encoded across different network layers, merging multiple saliency maps into a high-quality final output that functions as a CA ensemble. Benchmarks across two challenging medical datasets demonstrate the competitiveness of our multi-level CA approach compared to established models in the deep SOD literature.
]]></description>
<dc:subject>cellular-automata image-processing rather-interesting to-understand to-simulate consider:representation consider:dynamics metaheuristics classification image-segmentation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c02405c5a0f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<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: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:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.04298">
    <title>[2107.04298] An Algorithm for Reversible Logic Circuit Synthesis Based on Tensor Decomposition</title>
    <dc:date>2026-05-24T11:15:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.04298</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[An algorithm for reversible logic synthesis is proposed. The task is, for a given n-bit substitution map Pn:{0,1}n→{0,1}n, to find a sequence of reversible logic gates that implements the map. The gate library adopted in this work consists of multiple-controlled Toffoli gates denoted by CmX, where m is the number of control bits that ranges from 0 to n−1. Controlled gates with large m(>2) are then further decomposed into C0X, C1X, and C2X gates. A primary concern in designing the algorithm is to reduce the use of C2X gate (also known as Toffoli gate) which is known to be universal.
The main idea is to view an n-bit substitution map as a rank-2n tensor and to transform it such that the resulting map can be written as a tensor product of a rank-(2n−2) tensor and the 2×2 identity matrix. Let n be a set of all n-bit substitution maps. What we try to find is a size reduction map red:n→{Pn:Pn=Pn−1⊗I2}. %, where Im is the m×m identity matrix. One can see that the output Pn−1⊗I2 acts nontrivially on n−1 bits only, meaning that the map to be synthesized becomes Pn−1. The size reduction process is iteratively applied until it reaches tensor product of only 2×2 matrices.
]]></description>
<dc:subject>circuit-synthesis quantum-computing engineering-design rather-interesting cellular-automata metaheuristics to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a1381ee122ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:circuit-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quantum-computing"/>
	<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:cellular-automata"/>
	<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:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2407.03510">
    <title>[2407.03510] Evolutionary Approach to S-box Generation: Optimizing Nonlinear Substitutions in Symmetric Ciphers</title>
    <dc:date>2026-05-24T11:07:26+00:00</dc:date>
    <link>https://arxiv.org/abs/2407.03510</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This study explores the application of genetic algorithms in generating highly nonlinear substitution boxes (S-boxes) for symmetric key cryptography. We present a novel implementation that combines a genetic algorithm with the Walsh-Hadamard Spectrum (WHS) cost function to produce 8x8 S-boxes with a nonlinearity of 104. Our approach achieves performance parity with the best-known methods, requiring an average of 49,399 iterations with a 100% success rate. The study demonstrates significant improvements over earlier genetic algorithm implementations in this field, reducing iteration counts by orders of magnitude. By achieving equivalent performance through a different algorithmic approach, our work expands the toolkit available to cryptographers and highlights the potential of genetic methods in cryptographic primitive generation. The adaptability and parallelization potential of genetic algorithms suggest promising avenues for future research in S-box generation, potentially leading to more robust, efficient, and innovative cryptographic systems. Our findings contribute to the ongoing evolution of symmetric key cryptography, offering new perspectives on optimizing critical components of secure communication systems.
]]></description>
<dc:subject>metaheuristics evolutionary-algorithms cryptography rather-interesting to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:64007245b44e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cryptography"/>
	<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/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/s41467-025-59288-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://www.nature.com/articles/s41586-023-06600-9?ref=longnow.org">
    <title>Assembly theory explains and quantifies selection and evolution | Nature</title>
    <dc:date>2025-04-13T19:27:57+00:00</dc:date>
    <link>https://www.nature.com/articles/s41586-023-06600-9?ref=longnow.org</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Scientists have grappled with reconciling biological evolution1,2 with the immutable laws of the Universe defined by physics. These laws underpin life’s origin, evolution and the development of human culture and technology, yet they do not predict the emergence of these phenomena. Evolutionary theory explains why some things exist and others do not through the lens of selection. To comprehend how diverse, open-ended forms can emerge from physics without an inherent design blueprint, a new approach to understanding and quantifying selection is necessary3,4,5. We present assembly theory (AT) as a framework that does not alter the laws of physics, but redefines the concept of an ‘object’ on which these laws act. AT conceptualizes objects not as point particles, but as entities defined by their possible formation histories. This allows objects to show evidence of selection, within well-defined boundaries of individuals or selected units. We introduce a measure called assembly (A), capturing the degree of causation required to produce a given ensemble of objects. This approach enables us to incorporate novelty generation and selection into the physics of complex objects. It explains how these objects can be characterized through a forward dynamical process considering their assembly. By reimagining the concept of matter within assembly spaces, AT provides a powerful interface between physics and biology. It discloses a new aspect of physics emerging at the chemical scale, whereby history and causal contingency influence what exists.

]]></description>
<dc:subject>assembly-theory self-organization metaheuristics evolutionary-algorithms stochastic-systems rather-interesting exploration-and-exploitation to-understand to-write-about consider:tuning cause-and-effect</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4c5c085b1e97/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:assembly-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-organization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stochastic-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration-and-exploitation"/>
	<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:tuning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cause-and-effect"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2109.13103">
    <title>[2109.13103] Efficiently solving the thief orienteering problem with a max-min ant colony optimization approach</title>
    <dc:date>2024-11-16T14:50:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2109.13103</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We tackle the Thief Orienteering Problem (ThOP), an academic multi-component problem that combines two classical combinatorial problems, namely the Knapsack Problem and the Orienteering Problem. In the ThOP, a thief has a time limit to steal items that distributed in a given set of cities. While traveling, the thief collects items by storing them in their knapsack, which in turn reduces the travel speed. The thief has as the objective to maximize the total profit of the stolen items. In this article, we present an approach that combines swarm-intelligence with a randomized packing heuristic. Our solution approach outperforms existing works on almost all the 432 benchmarking instances, with significant improvements.
]]></description>
<dc:subject>multiobjective-optimization operations-research computational-complexity rather-interesting metaheuristics to-write-about consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:674b873506e1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<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:performance-measures"/>
</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/2303.06524v4">
    <title>[2303.06524v4] A heuristic search algorithm for discovering large Condorcet domains</title>
    <dc:date>2024-07-21T14:26:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2303.06524v4</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The study of large Condorcet domains (CD) has been a significant area of interest in voting theory. In this paper, our goal is to search for large CDs that are hitherto unknown. With a straightforward combinatorial definition, searching for large CDs is naturally suited for algorithmic optimisations. For each value of n>2, one can ask for the size of the largest CD, thus finding the largest CDs provides an important benchmark for heuristic-based combinatorial optimisation algorithms. Despite extensive research over the past three decades, the CD sizes identified in 1996 remain the best known for many values of n. When n>8, conducting an exhaustive search becomes computationally unfeasible, thereby prompting the use of heuristic methods. To address this, we developed a novel heuristic search algorithm in which a specially designed heuristic function, backed by a lookup database, directs the search towards promising branches in the search tree. Our algorithm found new large CDs of size 1082 (surpassing the previous record of 1069) for n=10, and 2349 (improving the previous 2324) for n=11. Notably, these newly discovered CDs exhibit characteristics distinct from those of known CDs.]]></description>
<dc:subject>permutations combinatorics metaheuristics rather-interesting looking-to-see enumeration to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1bbab28907e4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:permutations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:enumeration"/>
	<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/2212.06313">
    <title>[2212.06313] Metaheuristic-based Energy-aware Image Compression for Mobile App Development</title>
    <dc:date>2023-12-30T13:41:26+00:00</dc:date>
    <link>https://arxiv.org/abs/2212.06313</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The JPEG standard is widely used in different image processing applications. One of the main components of the JPEG standard is the quantisation table (QT) since it plays a vital role in the image properties such as image quality and file size. In recent years, several efforts based on population-based metaheuristic (PBMH) algorithms have been performed to find the proper QT(s) for a specific image, although they do not take into consideration the user opinion in advance. Take an android developer as an example, who prefers a small-size image, while the optimisation process results in a high-quality image, leading to a huge file size. Another pitfall of the current works is a lack of comprehensive coverage, meaning that the QT(s) can not provide all possible combinations of file size and quality. Therefore, this paper aims to propose three distinct contributions. First, to include the user opinion in the compression process, the file size of the output image can be controlled by a user in advance. To this end, we propose a novel objective function for population-based JPEG image compression. Second, to tackle the lack of comprehensive coverage, we suggest a novel representation. Our proposed representation can not only provide more comprehensive coverage but also find the proper value for the quality factor for a specific image without any background knowledge. Both changes in representation and objective function are independent of the search strategies and can be used with any type of population-based metaheuristic (PBMH) algorithm. Therefore, as the third contribution, we also provide a comprehensive benchmark on 22 state-of-the-art and recently-introduced PBMH algorithms. Our extensive experiments on different benchmark images and in terms of different criteria show that our novel formulation for JPEG image compression can work effectively.
]]></description>
<dc:subject>image-processing compression multiobjective-optimization rather-interesting metaheuristics to-write-about nudge-targets consider:animation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e5e672974303/</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:compression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<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:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:animation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2304.07089">
    <title>[2304.07089] Analyzing the Interaction Between Down-Sampling and Selection</title>
    <dc:date>2023-08-13T11:12:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2304.07089</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Genetic programming systems often use large training sets to evaluate the quality of candidate solutions for selection. However, evaluating populations on large training sets can be computationally expensive. Down-sampling training sets has long been used to decrease the computational cost of evaluation in a wide range of application domains. Indeed, recent studies have shown that both random and informed down-sampling can substantially improve problem-solving success for GP systems that use the lexicase parent selection algorithm. We use the PushGP framework to experimentally test whether these down-sampling techniques can also improve problem-solving success in the context of two other commonly used selection methods, fitness-proportionate and tournament selection, across eight GP problems (four program synthesis and four symbolic regression). We verified that down-sampling can benefit the problem-solving success of both fitness-proportionate and tournament selection. However, the number of problems wherein down-sampling improved problem-solving success varied by selection scheme, suggesting that the impact of down-sampling depends both on the problem and choice of selection scheme. Surprisingly, we found that down-sampling was most consistently beneficial when combined with lexicase selection as compared to tournament and fitness-proportionate selection. Overall, our results suggest that down-sampling should be considered more often when solving test-based GP problems.
]]></description>
<dc:subject>lexicase genetic-programming sampling metaheuristics performance-measure hey-I-know-this-guy to-write-about consider:counting-solutions consider:landscape consider:multiobjective-tradeoffs</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:70902eeeb474/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lexicase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<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:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:counting-solutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:landscape"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:multiobjective-tradeoffs"/>
</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/2207.09618">
    <title>[2207.09618] Dynamical system-based computational models for solving combinatorial optimization on hypergraphs</title>
    <dc:date>2023-07-30T16:19:14+00:00</dc:date>
    <link>https://arxiv.org/abs/2207.09618</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The intrinsic energy minimization in dynamical systems offers a valuable tool for minimizing the objective functions of computationally challenging problems in combinatorial optimization. However, most prior works have focused on mapping such dynamics to combinatorial optimization problems whose objective functions have quadratic degree (e.g., MaxCut); such problems can be represented and analyzed using graphs. However, the work on developing such models for problems that need objective functions with degree greater than two, and subsequently, entail the use of hypergraph data structures, is relatively sparse. In this work, we develop dynamical system-inspired computational models for several such problems. Specifically, we define the 'energy function' for hypergraph-based combinatorial problems ranging from Boolean SAT and its variants to integer factorization, and subsequently, define the resulting system dynamics. We also show that the design approach is applicable to optimization problems with quadratic degree, and use it develop a new dynamical system formulation for minimizing the Ising Hamiltonian. Our work not only expands on the scope of problems that can be directly mapped to, and solved using physics-inspired models, but also creates new opportunities to design high-performance accelerators for solving combinatorial optimization.
]]></description>
<dc:subject>optimization computational-complexity metaheuristics rather-interesting numerical-methods hypergraphs representation distributed-processing to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f9687f995259/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distributed-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2008.06530">
    <title>[2008.06530] On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD</title>
    <dc:date>2022-05-14T12:55:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2008.06530</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning has become a widely popular and successful paradigm, including in data-driven science and engineering. A major application problem is data-driven forecasting of future states from a complex dynamical. Artificial neural networks (ANN) have evolved as a clear leader amongst many machine learning approaches, and recurrent neural networks (RNN) are considered to be especially well suited for forecasting dynamical systems. In this setting, the echo state networks (ESN) or reservoir computer (RC) have emerged for their simplicity and computational complexity advantages. Instead of a fully trained network, an RC trains only read-out weights by a simple, efficient least squares method. What is perhaps quite surprising is that nonetheless an RC succeeds to make high quality forecasts, competitively with more intensively trained methods, even if not the leader. There remains an unanswered question as to why and how an RC works at all, despite randomly selected weights. We explicitly connect the RC with linear activation and linear read-out to well developed time-series literature on vector autoregressive averages (VAR) that includes theorems on representability through the WOLD theorem, which already perform reasonably for short term forecasts. In the case of a linear activation and now popular quadratic read-out RC, we explicitly connect to a nonlinear VAR (NVAR), which performs quite well. Further, we associate this paradigm to the now widely popular dynamic mode decomposition (DMD), and thus these three are in a sense different faces of the same thing. We illustrate our observations in terms of popular benchmark examples including Mackey-Glass differential delay equations and the Lorenz63 system.
]]></description>
<dc:subject>reservoir-computing machine-learning nonlinear-dynamics to-understand metaheuristics no-really-I-don't-understand-it-either</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a401326ff730/</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:nonlinear-dynamics"/>
	<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:no-really-I-don't-understand-it-either"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.07957">
    <title>[2105.07957] Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers</title>
    <dc:date>2022-03-13T11:06:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.07957</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A key feature of intelligent behaviour is the ability to learn abstract strategies that scale and transfer to unfamiliar problems. An abstract strategy solves every sample from a problem class, no matter its representation or complexity -- like algorithms in computer science. Neural networks are powerful models for processing sensory data, discovering hidden patterns, and learning complex functions, but they struggle to learn such iterative, sequential or hierarchical algorithmic strategies. Extending neural networks with external memories has increased their capacities in learning such strategies, but they are still prone to data variations, struggle to learn scalable and transferable solutions, and require massive training data. We present the Neural Harvard Computer (NHC), a memory-augmented network based architecture, that employs abstraction by decoupling algorithmic operations from data manipulations, realized by splitting the information flow and separated modules. This abstraction mechanism and evolutionary training enable the learning of robust and scalable algorithmic solutions. On a diverse set of 11 algorithms with varying complexities, we show that the NHC reliably learns algorithmic solutions with strong generalization and abstraction: perfect generalization and scaling to arbitrary task configurations and complexities far beyond seen during training, and being independent of the data representation and the task domain.
]]></description>
<dc:subject>machine-learning neural-networks metaheuristics program-synthesis wheels-reinvented to-write-about to-visualize consider:revisiting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b4c6ec760ac0/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:program-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wheels-reinvented"/>
	<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:revisiting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.04672">
    <title>[1810.04672] Evolutionary aspects of Reservoir Computing</title>
    <dc:date>2022-03-11T11:41:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.04672</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Reservoir Computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a reservoir with highly non-linear dynamics that does not require a fine tuning of its parts. These dynamics project input signals into high-dimensional spaces, where training linear readouts to extract input features is vastly simplified. Thus, inexpensive learning provides very powerful tools for decision making, controlling dynamical systems, classification, etc. RC also facilitates solving multiple tasks in parallel, resulting in a high throughput. Existing literature focuses on applications in artificial intelligence and neuroscience. We review this literature from an evolutionary perspective. RC's versatility make it a great candidate to solve outstanding problems in biology, which raises relevant questions: Is RC as abundant in Nature as its advantages should imply? Has it evolved? Once evolved, can it be easily sustained? Under what circumstances? (In other words, is RC an evolutionarily stable computing paradigm?) To tackle these issues we introduce a conceptual morphospace that would map computational selective pressures that could select for or against RC and other computing paradigms. This guides a speculative discussion about the questions above and allows us to propose a solid research line that brings together computation and evolution with RC as a working bench.
]]></description>
<dc:subject>metaheuristics to-understand machine-learning will-read reservoir-computing biological-engineering distributed-processing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ce15e2ddce6d/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:will-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biological-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distributed-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2009.00363">
    <title>[2009.00363] A Benchmark for Multi-UAV Task Assignment of an Extended Team Orienteering Problem</title>
    <dc:date>2022-03-02T11:33:43+00:00</dc:date>
    <link>https://arxiv.org/abs/2009.00363</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A benchmark for multi-UAV task assignment is presented in order to evaluate different algorithms. An extended Team Orienteering Problem is modeled for a kind of multi-UAV task assignment problem. Three intelligent algorithms, i.e., Genetic Algorithm, Ant Colony Optimization and Particle Swarm Optimization are implemented to solve the problem. A series of experiments with different settings are conducted to evaluate three algorithms. The modeled problem and the evaluation results constitute a benchmark, which can be used to evaluate other algorithms used for multi-UAV task assignment problems.
]]></description>
<dc:subject>metaheuristics horse-races algorithms rather-interesting operations-research to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4b5f407f9d68/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<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:operations-research"/>
	<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/1705.08691">
    <title>[1705.08691] General Algorithmic Search</title>
    <dc:date>2022-02-28T14:06:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.08691</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we present a metaheuristic for global optimization called General Algorithmic Search (GAS). Specifically, GAS is a stochastic, single-objective method that evolves a swarm of agents in search of a global extremum. Numerical simulations with a sample of 31 test functions show that GAS outperforms Basin Hopping, Cuckoo Search, and Differential Evolution, especially in concurrent optimization, i.e., when several runs with different initial settings are executed and the first best wins. Python codes of all algorithms and complementary information are available online.
]]></description>
<dc:subject>metaheuristics choosing-your-foes-very-carefully horse-races to-write-about consider:actually-checking consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4ad5ebbbdd8e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:choosing-your-foes-very-carefully"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:actually-checking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.09563">
    <title>[2106.09563] On Anytime Learning at Macroscale</title>
    <dc:date>2022-01-14T16:18:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.09563</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Classical machine learning frameworks assume access to a possibly large dataset in order to train a predictive model. In many practical applications however, data does not arrive all at once, but in batches over time. This creates a natural trade-off between accuracy of a model and time to obtain such a model. A greedy predictor could produce non-trivial predictions by immediately training on batches as soon as these become available but, it may also make suboptimal use of future data. On the other hand, a tardy predictor could wait for a long time to aggregate several batches into a larger dataset, but ultimately deliver a much better performance. In this work, we consider such a streaming learning setting, which we dub anytime learning at macroscale} (ALMA). It is an instance of anytime learning applied not at the level of a single chunk of data, but at the level of the entire sequence of large batches. We first formalize this learning setting, we then introduce metrics to assess how well learners perform on the given task for a given memory and compute budget, and finally we test about thirty baseline approaches on three standard benchmarks repurposed for anytime learning at macroscale. Our findings indicate that no model strikes the best trade-off across the board. While replay-based methods attain the lowest error rate, they also incur in a 5 to 10 times increase of compute. Approaches that grow capacity over time do offer better scaling in terms of training flops, but they also underperform simpler ensembling methods in terms of error rate. Overall, ALMA offers both a good abstraction of the typical learning setting faced everyday by practitioners, and a set of unsolved modeling problems for those interested in efficient learning of dynamic models.
]]></description>
<dc:subject>machine-learning metaheuristics batch-learning parametrization to-write-about see-also:coevolution</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:beeff3f0975a/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:batch-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:parametrization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:see-also:coevolution"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.05236">
    <title>[1810.05236] Practical Design Space Exploration</title>
    <dc:date>2021-08-07T11:39:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.05236</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Multi-objective optimization is a crucial matter in computer systems design space exploration because real-world applications often rely on a trade-off between several objectives. Derivatives are usually not available or impractical to compute and the feasibility of an experiment can not always be determined in advance. These problems are particularly difficult when the feasible region is relatively small, and it may be prohibitive to even find a feasible experiment, let alone an optimal one. 
We introduce a new methodology and corresponding software framework, HyperMapper 2.0, which handles multi-objective optimization, unknown feasibility constraints, and categorical/ordinal variables. This new methodology also supports injection of the user prior knowledge in the search when available. All of these features are common requirements in computer systems but rarely exposed in existing design space exploration systems. The proposed methodology follows a white-box model which is simple to understand and interpret (unlike, for example, neural networks) and can be used by the user to better understand the results of the automatic search. 
We apply and evaluate the new methodology to the automatic static tuning of hardware accelerators within the recently introduced Spatial programming language, with minimization of design run-time and compute logic under the constraint of the design fitting in a target field-programmable gate array chip. Our results show that HyperMapper 2.0 provides better Pareto fronts compared to state-of-the-art baselines, with better or competitive hypervolume indicator and with 8x improvement in sampling budget for most of the benchmarks explored.
]]></description>
<dc:subject>multiobjective-optimization exploration-and-exploitation rather-interesting algorithms metaheuristics performance-measure to-write-about to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cd49c7035aac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration-and-exploitation"/>
	<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:metaheuristics"/>
	<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-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.06339">
    <title>[2002.06339] Memristive oscillatory circuits for resolution of NP-complete logic puzzles: Sudoku case</title>
    <dc:date>2021-07-08T10:31:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.06339</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Memristor networks are capable of low-power and massive parallel processing and information storage. Moreover, they have presented the ability to apply for a vast number of intelligent data analysis applications targeting mobile edge devices and low power computing. Beyond the memory and conventional computing architectures, memristors are widely studied in circuits aiming for increased intelligence that are suitable to tackle complex problems in a power and area efficient manner, offering viable solutions oftenly arriving also from the biological principles of living organisms. In this paper, a memristive circuit exploiting the dynamics of oscillating networks is utilized for the resolution of very popular and NP-complete logic puzzles, like the well-known "Sudoku". More specifically, the proposed circuit design methodology allows for appropriate usage of interconnections' advantages in a oscillation network and of memristor's switching dynamics resulting to logic-solvable puzzle-instances. The reduced complexity of the proposed circuit and its increased scalability constitute its main advantage against previous approaches and the broadly presented SPICE based simulations provide a clear proof of concept of the aforementioned appealing characteristics.
]]></description>
<dc:subject>nonlinear-dynamics metaheuristics analog-computing rather-interesting to-simulate constraint-satisfaction to-visualize consider:cellular-neural-networks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b3146b867997/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:analog-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:cellular-neural-networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.02262">
    <title>[2102.02262] Modular Design of Hexagonal Phased Arrays Through Diamond Tiles</title>
    <dc:date>2021-07-04T11:36:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.02262</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The modular design of planar phased array antennas with hexagonal apertures is addressed by means of innovative diamond-shaped tiling techniques. Both tiling configuration and subarray coefficients are optimized to fit user-defined power-mask constraints on the radiation pattern. Toward this end, suitable surface-tiling mathematical theorems are customized to the problem at hand to guarantee optimal performance in case of low/medium-size arrays, while the computationally hard tiling of large arrays is yielded thanks to an effective integer-coded GA-based exploration of the arising high-cardinality solution spaces. By considering ideal as well as real array models, a set of representative benchmark problems is dealt with to assess the effectiveness of the proposed architectures and tiling strategies. Moreover, comparisons with alternative tiling architectures are also performed to show to the interested readers the advantages and the potentialities of the diamond subarraying of hexagonal apertures.
]]></description>
<dc:subject>electromagnetism antenna-design modular-design rather-interesting modeling-is-not-mathematics to-write-about nudge-targets consider:performance-measures consider:manufacturability evolutionary-algorithms metaheuristics emergent-design</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:72c9df3d2848/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:electromagnetism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:antenna-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modular-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:manufacturability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:emergent-design"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2005.05955">
    <title>[2005.05955] RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks</title>
    <dc:date>2020-09-23T14:36:25+00:00</dc:date>
    <link>https://arxiv.org/abs/2005.05955</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces the loss on a mini-batch. If this reduces the loss, the weight is updated, otherwise the existing weight is retained. Surprisingly, we find that repeating this process a few times for each weight is sufficient to train a deep neural network. The number of weight updates for RSO is an order of magnitude lesser when compared to backpropagation with SGD. RSO can make aggressive weight updates in each step as there is no concept of learning rate. The weight update step for individual layers is also not coupled with the magnitude of the loss. RSO is evaluated on classification tasks on MNIST and CIFAR-10 datasets with deep neural networks of 6 to 10 layers where it achieves an accuracy of 99.1% and 81.8% respectively. We also find that after updating the weights just 5 times, the algorithm obtains a classification accuracy of 98% on MNIST.
]]></description>
<dc:subject>machine-learning wheels-reinvented hill-climbing neural-networks metaheuristics to-write-about to-simulate consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b031fb1f099d/</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:wheels-reinvented"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hill-climbing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<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:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.00205">
    <title>[1907.00205] The Ramanujan Machine: Automatically Generated Conjectures on Fundamental Constants</title>
    <dc:date>2020-08-05T17:38:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.00205</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Fundamental mathematical constants like e and π are ubiquitous in diverse fields of science, from abstract mathematics to physics, biology and chemistry. For centuries, new formulas relating fundamental constants have been scarce and usually discovered sporadically. Here we propose a novel and systematic approach that leverages algorithms for deriving mathematical formulas for fundamental constants and help reveal their underlying structure. Our algorithms find dozens of well-known as well as previously unknown continued fraction representations of π, e, Catalan's constant, and values of the Riemann zeta function. Two example conjectures found by our algorithm and so far unproven are:
24π2=2+7⋅0⋅1+8⋅142+7⋅1⋅2+8⋅242+7⋅2⋅3+8⋅342+7⋅3⋅4+8⋅44..,87ζ(3)=1⋅1−163⋅7−265⋅19−367⋅37−46..
We present two algorithms that proved useful in finding conjectures: a Meet-In-The-Middle (MITM) algorithm and a Gradient Descent (GD) tailored to the recurrent structure of continued fractions. Both algorithms are based on matching numerical values and thus they conjecture formulas without providing proofs and without requiring prior knowledge on any underlying mathematical structure. This approach is especially attractive for constants for which no mathematical structure is known, as it reverses the conventional approach of sequential logic in formal proofs. Instead, our work supports a different approach for research: algorithms utilizing numerical data to unveil mathematical structures, thus trying to play the role of intuition of great mathematicians of the past, providing leads to new mathematical research.
]]></description>
<dc:subject>continued-fractions metaheuristics approximation rather-interesting experimental-mathematics proof-systems to-write-about to-simulate consider:representation consider:performance-measures consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1af9f125d57f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:continued-fractions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experimental-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:proof-systems"/>
	<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:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<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/1810.02334">
    <title>[1810.02334] Unsupervised Learning via Meta-Learning</title>
    <dc:date>2020-05-21T11:52:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.02334</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised meta-learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-learning over the constructed tasks. Surprisingly, we find that, when integrated with meta-learning, relatively simple task construction mechanisms, such as clustering embeddings, lead to good performance on a variety of downstream, human-specified tasks. Our experiments across four image datasets indicate that our unsupervised meta-learning approach acquires a learning algorithm without any labeled data that is applicable to a wide range of downstream classification tasks, improving upon the embedding learned by four prior unsupervised learning methods.
]]></description>
<dc:subject>meta-optimization unsupervised-learning rather-interesting novelty-search-kinda metaheuristics to-simulate to-write-about consider:generalizations consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:eb3a5c53990c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meta-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:novelty-search-kinda"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:generalizations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.05628">
    <title>[2002.05628] XCS Classifier System with Experience Replay</title>
    <dc:date>2020-05-21T11:48:12+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.05628</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[XCS constitutes the most deeply investigated classifier system today. It bears strong potentials and comes with inherent capabilities for mastering a variety of different learning tasks. Besides outstanding successes in various classification and regression tasks, XCS also proved very effective in certain multi-step environments from the domain of reinforcement learning. Especially in the latter domain, recent advances have been mainly driven by algorithms which model their policies based on deep neural networks -- among which the Deep-Q-Network (DQN) is a prominent representative. Experience Replay (ER) constitutes one of the crucial factors for the DQN's successes, since it facilitates stabilized training of the neural network-based Q-function approximators. Surprisingly, XCS barely takes advantage of similar mechanisms that leverage stored raw experiences encountered so far. To bridge this gap, this paper investigates the benefits of extending XCS with ER. On the one hand, we demonstrate that for single-step tasks ER bears massive potential for improvements in terms of sample efficiency. On the shady side, however, we reveal that the use of ER might further aggravate well-studied issues not yet solved for XCS when applied to sequential decision problems demanding for long-action-chains.
]]></description>
<dc:subject>classifier-systems evolutionary-algorithms machine-learning metaheuristics rather-interesting to-understand to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fdbc2718c927/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classifier-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<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: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-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1806.09935">
    <title>[1806.09935] On the performance of multi-objective estimation of distribution algorithms for combinatorial problems</title>
    <dc:date>2020-05-18T21:36:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1806.09935</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Fitness landscape analysis investigates features with a high influence on the performance of optimization algorithms, aiming to take advantage of the addressed problem characteristics. In this work, a fitness landscape analysis using problem features is performed for a Multi-objective Bayesian Optimization Algorithm (mBOA) on instances of MNK-landscape problem for 2, 3, 5 and 8 objectives. We also compare the results of mBOA with those provided by NSGA-III through the analysis of their estimated runtime necessary to identify an approximation of the Pareto front. Moreover, in order to scrutinize the probabilistic graphic model obtained by mBOA, the Pareto front is examined according to a probabilistic view. The fitness landscape study shows that mBOA is moderately or loosely influenced by some problem features, according to a simple and a multiple linear regression model, which is being proposed to predict the algorithms performance in terms of the estimated runtime. Besides, we conclude that the analysis of the probabilistic graphic model produced at the end of evolution can be useful to understand the convergence and diversity performances of the proposed approach.
]]></description>
<dc:subject>metaheuristics evolutionary-algorithms multiobjective-optimization looking-to-see rather-interesting to-write-about to-simulate consider:dimensionality</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1bf9a9cbb612/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<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:looking-to-see"/>
	<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:consider:dimensionality"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.09813">
    <title>[1904.09813] Algorithm Portfolio for Individual-based Surrogate-Assisted Evolutionary Algorithms</title>
    <dc:date>2020-05-09T12:03:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.09813</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Surrogate-assisted evolutionary algorithms (SAEAs) are powerful optimisation tools for computationally expensive problems (CEPs). However, a randomly selected algorithm may fail in solving unknown problems due to no free lunch theorems, and it will cause more computational resource if we re-run the algorithm or try other algorithms to get a much solution, which is more serious in CEPs. In this paper, we consider an algorithm portfolio for SAEAs to reduce the risk of choosing an inappropriate algorithm for CEPs. We propose two portfolio frameworks for very expensive problems in which the maximal number of fitness evaluations is only 5 times of the problem's dimension. One framework named Par-IBSAEA runs all algorithm candidates in parallel and a more sophisticated framework named UCB-IBSAEA employs the Upper Confidence Bound (UCB) policy from reinforcement learning to help select the most appropriate algorithm at each iteration. An effective reward definition is proposed for the UCB policy. We consider three state-of-the-art individual-based SAEAs on different problems and compare them to the portfolios built from their instances on several benchmark problems given limited computation budgets. Our experimental studies demonstrate that our proposed portfolio frameworks significantly outperform any single algorithm on the set of benchmark problems.
]]></description>
<dc:subject>metaheuristics meta-optimization hedging rather-interesting algorithms to-write-about to-simulate consider:toy-examples consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:64336a2c070a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meta-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hedging"/>
	<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-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:toy-examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.05755">
    <title>[1901.05755] Voronoi-based Efficient Surrogate-assisted Evolutionary Algorithm for Very Expensive Problems</title>
    <dc:date>2020-05-09T12:00:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.05755</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Very expensive problems are very common in practical system that one fitness evaluation costs several hours or even days. Surrogate assisted evolutionary algorithms (SAEAs) have been widely used to solve this crucial problem in the past decades. However, most studied SAEAs focus on solving problems with a budget of at least ten times of the dimension of problems which is unacceptable in many very expensive real-world problems. In this paper, we employ Voronoi diagram to boost the performance of SAEAs and propose a novel framework named Voronoi-based efficient surrogate assisted evolutionary algorithm (VESAEA) for very expensive problems, in which the optimization budget, in terms of fitness evaluations, is only 5 times of the problem's dimension. In the proposed framework, the Voronoi diagram divides the whole search space into several subspace and then the local search is operated in some potentially better subspace. Additionally, in order to trade off the exploration and exploitation, the framework involves a global search stage developed by combining leave-one-out cross-validation and radial basis function surrogate model. A performance selector is designed to switch the search dynamically and automatically between the global and local search stages. The empirical results on a variety of benchmark problems demonstrate that the proposed framework significantly outperforms several state-of-art algorithms with extremely limited fitness evaluations. Besides, the efficacy of Voronoi-diagram is furtherly analyzed, and the results show its potential to optimize very expensive problems.
]]></description>
<dc:subject>experimental-design metaheuristics computational-geometry rather-interesting training-data constraint-satisfaction approximation to-write-about to-simulate consider:basic-visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:83d14eab49ca/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:training-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<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:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:basic-visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://openreview.net/forum?id=S1sqHMZCb">
    <title>NerveNet: Learning Structured Policy with Graph Neural Networks | OpenReview</title>
    <dc:date>2020-05-06T11:30:57+00:00</dc:date>
    <link>https://openreview.net/forum?id=S1sqHMZCb</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Abstract: We address the problem of learning structured policies for continuous control. In traditional reinforcement learning, policies of agents are learned by MLPs which take the concatenation of all observations from the environment as input for predicting actions. In this work, we propose NerveNet to explicitly model the structure of an agent, which naturally takes the form of a graph. Specifically, serving as the agent's policy network, NerveNet first propagates information over the structure of the agent and then predict actions for different parts of the agent. In the experiments, we first show that our NerveNet is comparable to state-of-the-art methods on standard MuJoCo environments. We further propose our customized reinforcement learning environments for benchmarking two types of structure transfer learning tasks, i.e., size and disability transfer. We demonstrate that policies learned by NerveNet are significantly better than policies learned by other models and are able to transfer even in a zero-shot setting.
]]></description>
<dc:subject>neural-networks metaheuristics transfer-learning optimization operations-research to-write-about to-simulate consider:out-of-sample</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5cabd9a9ac94/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:transfer-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<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:out-of-sample"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.09670">
    <title>[1711.09670] Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting</title>
    <dc:date>2020-05-04T11:52:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.09670</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.
]]></description>
<dc:subject>OCR image-processing machine-learning collective-intelligence metaheuristics to-write-about to-simulate consider:preprocessing consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:01a08cd7c3af/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:OCR"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<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:metaheuristics"/>
	<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:preprocessing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.05045">
    <title>[1810.05045] Analysis of Noisy Evolutionary Optimization When Sampling Fails</title>
    <dc:date>2020-05-03T11:46:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.05045</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In noisy evolutionary optimization, sampling is a common strategy to deal with noise. By the sampling strategy, the fitness of a solution is evaluated multiple times (called \emph{sample size}) independently, and its true fitness is then approximated by the average of these evaluations. Previous studies on sampling are mainly empirical. In this paper, we first investigate the effect of sample size from a theoretical perspective. By analyzing the (1+1)-EA on the noisy LeadingOnes problem, we show that as the sample size increases, the running time can reduce from exponential to polynomial, but then return to exponential. This suggests that a proper sample size is crucial in practice. Then, we investigate what strategies can work when sampling with any fixed sample size fails. By two illustrative examples, we prove that using parent or offspring populations can be better. Finally, we construct an artificial noisy example to show that when using neither sampling nor populations is effective, adaptive sampling (i.e., sampling with an adaptive sample size) can work. This, for the first time, provides a theoretical support for the use of adaptive sampling.
]]></description>
<dc:subject>evolutionsstrategie evolutionary-algorithms optimization metaheuristics to-write-about guessing rather-interesting to-simulate consider:lexicase consider:parameter-smudge</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bb3ae405ea42/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionsstrategie"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<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:guessing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:parameter-smudge"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.00937">
    <title>[2002.00937] Radioactive data: tracing through training</title>
    <dc:date>2020-05-02T15:03:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.00937</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this dataset such that any model trained on it will bear an identifiable mark. The mark is robust to strong variations such as different architectures or optimization methods. Given a trained model, our technique detects the use of radioactive data and provides a level of confidence (p-value). Our experiments on large-scale benchmarks (Imagenet), using standard architectures (Resnet-18, VGG-16, Densenet-121) and training procedures, show that we can detect usage of radioactive data with high confidence (p<10^-4) even when only 1% of the data used to trained our model is radioactive. Our method is robust to data augmentation and the stochasticity of deep network optimization. As a result, it offers a much higher signal-to-noise ratio than data poisoning and backdoor methods.
]]></description>
<dc:subject>machine-learning data-analysis rather-interesting security looking-to-see metaheuristics privacy algorithms to-write-about to-simulate consider:parallels-for-other-metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5c006b02c3bb/</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:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<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:parallels-for-other-metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.04966">
    <title>[1910.04966] Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks (GANs)</title>
    <dc:date>2020-05-02T13:16:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.04966</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models. Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models. Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality. To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial networks (GANs). At each generation of the proposed algorithm, the parent solutions are first classified into real and fake samples to train the GANs; then the offspring solutions are sampled by the trained GANs. Thanks to the powerful generative ability of the GANs, our proposed algorithm is capable of generating promising offspring solutions in high-dimensional decision space with limited training data. The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables. Experimental results on these test problems demonstrate the effectiveness of the proposed algorithm.
]]></description>
<dc:subject>symbolic-regression neural-networks coevolution metaheuristics reinventing-the-wheel to-write-about pareto-GP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5522b744681b/</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:coevolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinventing-the-wheel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pareto-GP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.01218">
    <title>[1907.01218] Representing fitness landscapes by valued constraints to understand the complexity of local search</title>
    <dc:date>2020-03-08T19:19:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.01218</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Local search is widely used to solve combinatorial optimisation problems and to model biological evolution, but the performance of local search algorithms on different kinds of fitness landscapes is poorly understood. Here we introduce a natural approach to modelling fitness landscapes using valued constraints. This allows us to investigate minimal representations (normal forms) and to consider the effects of the structure of the constraint graph on the tractability of local search. First, we show that for fitness landscapes representable by binary Boolean valued constraints there is a minimal necessary constraint graph that can be easily computed. Second, we consider landscapes as equivalent if they allow the same (improving) local search moves; we show that a minimal normal form still exists, but is NP-hard to compute. Next we consider the complexity of local search on fitness landscapes modelled by valued constraints with restricted forms of constraint graph. In the binary Boolean case, we prove that a tree-structured constraint graph gives a tight quadratic bound on the number of improving moves made by any local search; hence, any landscape that can be represented by such a model will be tractable for local search. We build two families of examples to show that both the conditions in our tractability result are essential. With domain size three, even just a path of binary constraints can model a landscape with an exponentially long sequence of improving moves. With a treewidth two constraint graph, even with a maximum degree of three, binary Boolean constraints can model a landscape with an exponentially long sequence of improving moves.
]]></description>
<dc:subject>fitness-landscapes combinatorics metaheuristics representation rather-interesting to-write-about to-simulate consider:no-free-lunch consider:side-steps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:39d07fb7770f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<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: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:no-free-lunch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:side-steps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://htsang.wikidot.com/research">
    <title>DR. HERBERT H. TSANG - http://www.herberttsang.org</title>
    <dc:date>2020-02-09T01:14:49+00:00</dc:date>
    <link>http://htsang.wikidot.com/research</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[RNA design algorithm takes an RNA secondary structure description as input and then try to identify an RNA strand that folds into this function-specific target structure. With new advances in biotechnology and synthetic biology, a reliable RNA design algorithm can be crucial steps to create new biochemical components. Our lab is interested in employing various computational intelligence techniques to propose the new paradigm to help with the RNA design problem. Recently, we have designed an algorithm SIMARD, which is based on the simulated annealing paradigm.
]]></description>
<dc:subject>structural-biology polymer-folding biochemistry biophysics simulation metaheuristics energy-landscapes rather-interesting to-write-about to-simulate to-visualize</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d531cf9636cd/</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:polymer-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biochemistry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biophysics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:energy-landscapes"/>
	<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:to-visualize"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/0706.1754">
    <title>[0706.1754] Protein structure prediction by an iterative search method</title>
    <dc:date>2020-01-14T21:41:45+00:00</dc:date>
    <link>https://arxiv.org/abs/0706.1754</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We demonstrate a new algorithm for finding protein conformations that minimize a non-bonded energy function. The new algorithm, called the difference map, seeks to find an atomic configuration that is simultaneously in two constraint spaces. The first constraint space is the space of atomic configurations that have a valid peptide geometry, while the second is the space of configurations that have a non-bonded energy below a given target. These two constraint spaces are used to define a deterministic dynamical system, whose fixed points produce atomic configurations in the intersection of the two constraint spaces. The rate at which the difference map produces low energy protein conformations is compared with that of a contemporary search algorithm, parallel tempering. The results indicate the difference map finds low energy protein conformations at a significantly higher rate then parallel tempering.
]]></description>
<dc:subject>protein-folding heuristics hill-climbing rather-interesting metaheuristics old to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a9a0f4f2c4d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hill-climbing"/>
	<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:old"/>
	<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/1902.04692">
    <title>[1902.04692] Analysis of Baseline Evolutionary Algorithms for the Packing While Travelling Problem</title>
    <dc:date>2019-11-25T17:38:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1902.04692</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The performance of base-line Evolutionary Algorithms (EAs) on combinatorial problems has been studied rigorously. From the theoretical viewpoint, the literature extensively investigates the linear problems, while the theoretical analysis of the non-linear problems is still far behind. In this paper, variations of the Packing While Travelling (PWT) -- also known as the non-linear knapsack problem -- are studied as an attempt to analyse the behaviour of EAs on non-linear problems from theoretical perspective. We investigate PWT for two cities and n items with correlated weights and profits, using single-objective and multi-objective algorithms. Our results show that RLS\_swap, which differs from the classical RLS by having the ability to swap two bits in one iteration, finds the optimal solution in O(n3) expected time. We also study an enhanced version of GSEMO, which a specific selection operator to deal with exponential population size, and prove that it finds the Pareto front in the same asymptotic expected time. In the case of uniform weights, (1+1)~EA is able to find the optimal solution in expected time O(n2log(max{n,pmax})), where pmax is the largest profit of the given items. We also perform an experimental analysis to complement our theoretical investigations and provide additional insights into the runtime behavior.
]]></description>
<dc:subject>metaheuristics operations-research horse-races yet-another-combined-problem to-simulate to-write-about consider:performance-measures consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1f602e12f460/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:yet-another-combined-problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.07617">
    <title>[1608.07617] &quot;Sampling&quot;' as a Baseline Optimizer for Search-based Software Engineering</title>
    <dc:date>2019-08-30T10:59:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.07617</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Increasingly, Software Engineering (SE) researchers use search-based optimization techniques to solve SE problems with multiple conflicting objectives. These techniques often apply CPU-intensive evolutionary algorithms to explore generations of mutations to a population of candidate solutions. An alternative approach, proposed in this paper, is to start with a very large population and sample down to just the better solutions. We call this method "SWAY", short for "the sampling way". Sway is very simple to implement and, in studies with various software engineering models, this sampling approach was found to be competitive with corresponding state-of-the-art evolutionary algorithms while requiring far less computation cost. Considering the simplicity and effectiveness of Sway, we, therefore, propose this approach as a baseline method for search-based software engineering models, especially for models that are very slow to execute.
]]></description>
<dc:subject>metaheuristics genetic-programming multiobjective-optimization evolutionary-algorithms performance-measure rather-interesting search-operators to-write-about to-replicate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d1ada658a31a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<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:search-operators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-replicate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.08226">
    <title>[1907.08226] Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model</title>
    <dc:date>2019-08-06T09:35:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.08226</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Gradient-based algorithms are effective for many machine learning tasks, but despite ample recent effort and some progress, it often remains unclear why they work in practice in optimising high-dimensional non-convex functions and why they find good minima instead of being trapped in spurious ones. 
Here we present a quantitative theory explaining this behaviour in a spiked matrix-tensor model. 
Our framework is based on the Kac-Rice analysis of stationary points and a closed-form analysis of gradient-flow originating from statistical physics. We show that there is a well defined region of parameters where the gradient-flow algorithm finds a good global minimum despite the presence of exponentially many spurious local minima. 
We show that this is achieved by surfing on saddles that have strong negative direction towards the global minima, a phenomenon that is connected to a BBP-type threshold in the Hessian describing the critical points of the landscapes.
]]></description>
<dc:subject>machine-learning optimization fitness-landscapes metaheuristics representation to-understand topology dynamical-systems consider:performance-measures consider:better-faster</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c6507c15b09d/</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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<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:topology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:better-faster"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.01672">
    <title>[1807.01672] Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization</title>
    <dc:date>2019-08-06T09:11:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.01672</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increasing the importance of enabling the benefits of self-play beyond two-player games. We present the Ranked Reward (R2) algorithm which accomplishes this by ranking the rewards obtained by a single agent over multiple games to create a relative performance metric. Results from applying the R2 algorithm to instances of a two-dimensional and three-dimensional bin packing problems show that it outperforms generic Monte Carlo tree search, heuristic algorithms and integer programming solvers. We also present an analysis of the ranked reward mechanism, in particular, the effects of problem instances with varying difficulty and different ranking thresholds.
]]></description>
<dc:subject>machine-learning reinforcement-learning algorithms self-play mechanism-design optimization performance-measure to-understand operations-research metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:062f6ce17047/</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:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-play"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mechanism-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1905.03427">
    <title>[1905.03427] Variable Neighborhood Search for the Bin Packing Problem with Compatible Categories</title>
    <dc:date>2019-08-06T09:02:36+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.03427</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Bin Packing with Conflicts (BPC) are problems in which items with compatibility constraints must be packed in the least number of bins, not exceeding the capacity of the bins and ensuring that non-conflicting items are packed in each bin. In this work, we introduce the Bin Packing Problem with Compatible Categories (BPCC), a variant of the BPC in which items belong to conflicting or compatible categories, in opposition to the item-by-item incompatibility found in previous literature. It is a common problem in the context of last mile distribution to nanostores located in densely populated areas. To efficiently solve real-life sized instances of the problem, we propose a Variable Neighborhood Search (VNS) metaheuristic algorithm. Computational experiments suggest that the algorithm yields good solutions in very short times while compared to linear integer programming running on a high-performance computing environment.
]]></description>
<dc:subject>operations-research optimization constraint-satisfaction heuristics metaheuristics to-read to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e6f268e6f235/</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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.07983">
    <title>[1906.07983] Explanations can be manipulated and geometry is to blame</title>
    <dc:date>2019-06-26T09:51:59+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.07983</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to the input that keep the network's output approximately constant. We establish theoretically that this phenomenon can be related to certain geometrical properties of neural networks. This allows us to derive an upper bound on the susceptibility of explanations to manipulations. Based on this result, we propose effective mechanisms to enhance the robustness of explanations.
]]></description>
<dc:subject>neural-networks machine-learning well-duh adversarial-testing metaheuristics not-surprising-really-now-izzit?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:769b6de9565f/</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:well-duh"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adversarial-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:not-surprising-really-now-izzit?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.01312">
    <title>[1811.01312] Adversarial Black-Box Attacks for Automatic Speech Recognition Systems Using Multi-Objective Genetic Optimization</title>
    <dc:date>2019-06-12T13:18:01+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.01312</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Fooling deep neural networks with adversarial input have exposed a significant vulnerability in current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either replicate the model itself or to craft examples which cause the model to fail. In this work, we use a multi-objective genetic algorithm based approach to perform both targeted and un-targeted black-box attacks on automatic speech recognition (ASR) systems. The main contribution of this research is the proposal of a generic framework which can be used to attack any ASR system, even if it's internal working is hidden. 
During the un-targeted attacks, the Word Error Rates (WER) of the ASR degrades from 0.5 to 5.4, indicating the potency of our approach. In targeted attacks, our solution reaches a WER of 2.14. In both attacks, the adversarial samples maintain a high acoustic similarity of 0.98 and 0.97.
]]></description>
<dc:subject>metaheuristics adversarial-design speech-recognition algorithms coevolution evolutionary-algorithms to-write-about rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bcb89a4c3798/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adversarial-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:speech-recognition"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coevolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.03548">
    <title>[1802.03548] Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm</title>
    <dc:date>2019-06-12T13:15:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.03548</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The atomistic modeling of amorphous materials requires structure sizes and sampling statistics that are challenging to achieve with first-principles methods. Here, we propose a methodology to speed up the sampling of amorphous and disordered materials using a combination of a genetic algorithm and a specialized machine-learning potential based on artificial neural networks (ANN). We show for the example of the amorphous LiSi alloy that around 1,000 first-principles calculations are sufficient for the ANN potential assisted sampling of low-energy atomic configurations in the entire amorphous LixSi phase space. The obtained phase diagram is validated by comparison with the results from an extensive sampling of LixSi configurations using molecular dynamics simulations and a general ANN potential trained to ~45,000 first-principles calculations. This demonstrates the utility of the approach for the first-principles modeling of amorphous materials.
]]></description>
<dc:subject>metaheuristics materials-science engineering-design molecular-design rather-interesting simulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8a0bb15c5572/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:materials-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1806.03455">
    <title>[1806.03455] A Preliminary Exploration of Floating Point Grammatical Evolution</title>
    <dc:date>2019-05-02T08:52:47+00:00</dc:date>
    <link>https://arxiv.org/abs/1806.03455</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Current GP frameworks are highly effective on a range of real and simulated benchmarks. However, due to the high dimensionality of the genotypes for GP, the task of visualising the fitness landscape for GP search can be difficult. This paper describes a new framework: Floating Point Grammatical Evolution (FP-GE) which uses a single floating point genotype to encode an individual program. This encoding permits easier visualisation of the fitness landscape arbitrary problems by providing a way to map fitness against a single dimension. The new framework also makes it trivially easy to apply continuous search algorithms, such as Differential Evolution, to the search problem. In this work, the FP-GE framework is tested against several regression problems, visualising the search landscape for these and comparing different search meta-heuristics.
]]></description>
<dc:subject>metaheuristics grammatical-evolution representation horse-races to-write-about consider:robustness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:88d5f811a513/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:grammatical-evolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.03495">
    <title>[1807.03495] Significance-based Estimation-of-Distribution Algorithms</title>
    <dc:date>2019-05-02T08:48:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.03495</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Estimation-of-distribution algorithms (EDAs) are randomized search heuristics that maintain a probabilistic model of the solution space. This model is updated from iteration to iteration, based on the quality of the solutions sampled according to the model. As previous works show, this short-term perspective can lead to erratic updates of the model, in particular, to bit-frequencies approaching a random boundary value. Such frequencies take long to be moved back to the middle range, leading to significant performance losses. 
In order to overcome this problem, we propose a new EDA based on the classic compact genetic algorithm (cGA) that takes into account a longer history of samples and updates its model only with respect to information which it classifies as statistically significant. We prove that this significance-based compact genetic algorithm (sig-cGA) optimizes the commonly regarded benchmark functions OneMax, LeadingOnes, and BinVal all in O(nlogn) time, a result shown for no other EDA or evolutionary algorithm so far. 
For the recently proposed scGA -- an EDA that tries to prevent erratic model updates by imposing a bias to the uniformly distributed model -- we prove that it optimizes OneMax only in a time exponential in the hypothetical population size 1/ρ. Similarly, we show that the convex search algorithm cannot optimize OneMax in polynomial time.
]]></description>
<dc:subject>metaheuristics EDA rather-interesting algorithms performance-measure to-understand consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1e916fc8e3b6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:EDA"/>
	<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:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.08584">
    <title>[1810.08584] Reverse Quantum Annealing Approach to Portfolio Optimization Problems</title>
    <dc:date>2019-05-02T08:46:40+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.08584</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We investigate a hybrid quantum-classical solution method to the mean-variance portfolio optimization problems. Starting from real financial data statistics and following the principles of the Modern Portfolio Theory, we generate parametrized samples of portfolio optimization problems that can be related to quadratic binary optimization forms programmable in the analog D-Wave Quantum Annealer 2000Q. The instances are also solvable by an industry-established Genetic Algorithm approach, which we use as a classical benchmark. We investigate several options to run the quantum computation optimally, ultimately discovering that the best results in terms of expected time-to-solution as a function of number of variables for the hardest instances set are obtained by seeding the quantum annealer with a solution candidate found by a greedy local search and then performing a reverse annealing protocol. The optimized reverse annealing protocol is found to be more than 100 times faster than the corresponding forward quantum annealing on average.
]]></description>
<dc:subject>metaheuristics quantums portfolio-theory optimization algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d249eec01b12/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quantums"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:portfolio-theory"/>
	<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:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.05850">
    <title>[1808.05850] Towards a Theory-Guided Benchmarking Suite for Discrete Black-Box Optimization Heuristics: Profiling $(1+λ)$ EA Variants on OneMax and LeadingOnes</title>
    <dc:date>2019-04-23T11:08:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.05850</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Theoretical and empirical research on evolutionary computation methods complement each other by providing two fundamentally different approaches towards a better understanding of black-box optimization heuristics. In discrete optimization, both streams developed rather independently of each other, but we observe today an increasing interest in reconciling these two sub-branches. In continuous optimization, the COCO (COmparing Continuous Optimisers) benchmarking suite has established itself as an important platform that theoreticians and practitioners use to exchange research ideas and questions. No widely accepted equivalent exists in the research domain of discrete black-box optimization. 
Marking an important step towards filling this gap, we adjust the COCO software to pseudo-Boolean optimization problems, and obtain from this a benchmarking environment that allows a fine-grained empirical analysis of discrete black-box heuristics. In this documentation we demonstrate how this test bed can be used to profile the performance of evolutionary algorithms. More concretely, we study the optimization behavior of several (1+λ) EA variants on the two benchmark problems OneMax and LeadingOnes. This comparison motivates a refined analysis for the optimization time of the (1+λ) EA on LeadingOnes.
]]></description>
<dc:subject>evolutionary-algorithms metaheuristics horse-races performance-measure rather-interesting to-write-about consider:classification benchmarking consider:open-ended-problems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:535c083a1d4f/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<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:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:open-ended-problems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1707.04016">
    <title>[1707.04016] Dependency Injection for Programming by Optimization</title>
    <dc:date>2019-04-08T00:59:01+00:00</dc:date>
    <link>https://arxiv.org/abs/1707.04016</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Programming by Optimization tools perform automatic software configuration according to the specification supplied by a software developer. Developers specify design spaces for program components, and the onerous task of determining which configuration best suits a given use case is determined using automated analysis tools and optimization heuristics. However, in current approaches to Programming by Optimization, design space specification and exploration relies on external configuration algorithms, executable wrappers and fragile, preprocessed programming language extensions. 
Here we show that the architectural pattern of Dependency Injection provides a superior alternative to the traditional Programming by Optimization pipeline. We demonstrate that configuration tools based on Dependency Injection fit naturally into the software development process, while requiring less overhead than current wrapper-based mechanisms. Furthermore, the structural correspondence between Dependency Injection and context-free grammars yields a new class of evolutionary metaheuristics for automated algorithm configuration. We found that the new heuristics significantly outperform existing configuration algorithms on many problems of interest (in one case by two orders of magnitude). We anticipate that these developments will make Programming by Optimization immediately applicable to a large number of enterprise software projects.
]]></description>
<dc:subject>machine-learning generative-programming metaheuristics ant-colony-optimization rather-interesting to-implement via:Jerry-Swan</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:de91154bf41b/</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:generative-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ant-colony-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-implement"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:Jerry-Swan"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.02873">
    <title>[1812.02873] A new multilayer optical film optimal method based on deep q-learning</title>
    <dc:date>2019-03-12T11:08:17+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.02873</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Multi-layer optical film has been found to afford important applications in optical communication, optical absorbers, optical filters, etc. Different algorithms of multi-layer optical film design has been developed, as simplex method, colony algorithm, genetic algorithm. These algorithms rapidly promote the design and manufacture of multi-layer films. However, traditional numerical algorithms of converge to local optimum. This means that the algorithms can not give a global optimal solution to the material researchers. In recent years, due to the rapid development to far artificial intelligence, to optimize optical film structure using AI algorithm has become possible. In this paper, we will introduce a new optical film design algorithm based on the deep Q learning. This model can converge the global optimum of the optical thin film structure, this will greatly improve the design efficiency of multi-layer films.]]></description>
<dc:subject>engineering-design metaheuristics horse-races materials-science machine-learning applications</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d16c5d372e89/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:materials-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:applications"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.04491">
    <title>[1802.04491] Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Resource Management in 5G Networks</title>
    <dc:date>2019-03-09T13:32:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.04491</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the context of Fifth Generation (5G) mobile networks, the concept of "Slice as a Service" (SlaaS) promotes mobile network operators to flexibly share infrastructures with mobile service providers and stakeholders. However, it also challenges with an emerging demand for efficient online algorithms to optimize the request-and-decision-based inter-slice resource management strategy. Based on genetic algorithms, this paper presents a novel online optimizer that efficiently approaches towards the ideal slicing strategy with maximized long-term network utility. The proposed method encodes slicing strategies into binary sequences to cope with the request-and-decision mechanism. It requires no a priori knowledge about the traffic/utility models, and therefore supports heterogeneous slices, while providing solid effectiveness, good robustness against non-stationary service scenarios, and high scalability.
]]></description>
<dc:subject>evolutionary-algorithms metaheuristics QoS mobile-networks quality-of-service operations-research multiobjective-optimization to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:be8733fddd4b/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:QoS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mobile-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quality-of-service"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1809.07406">
    <title>[1809.07406] Exploiting Tournament Selection for Efficient Parallel Genetic Programming</title>
    <dc:date>2019-02-10T16:51:55+00:00</dc:date>
    <link>https://arxiv.org/abs/1809.07406</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Genetic Programming (GP) is a computationally intensive technique which is naturally parallel in nature. Consequently, many attempts have been made to improve its run-time from exploiting highly parallel hardware such as GPUs. However, a second methodology of improving the speed of GP is through efficiency techniques such as subtree caching. However achieving parallel performance and efficiency is a difficult task. This paper will demonstrate an efficiency saving for GP compatible with the harnessing of parallel CPU hardware by exploiting tournament selection. Significant efficiency savings are demonstrated whilst retaining the capability of a high performance parallel implementation of GP. Indeed, a 74% improvement in the speed of GP is achieved with a peak rate of 96 billion GPop/s for classification type problems.
]]></description>
<dc:subject>genetic-programming horse-races tournament-selection selection metaheuristics have-done to-write-about consider:deathless-GP-then-what consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5a312fb9b2dd/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:tournament-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:have-done"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:deathless-GP-then-what"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.00045">
    <title>[1703.00045] Aggregated knowledge from a small number of debates outperforms the wisdom of large crowds</title>
    <dc:date>2019-02-05T09:45:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.00045</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The aggregation of many independent estimates can outperform the most accurate individual judgment. This centenarian finding, popularly known as the wisdom of crowds, has been applied to problems ranging from the diagnosis of cancer to financial forecasting. It is widely believed that social influence undermines collective wisdom by reducing the diversity of opinions within the crowd. Here, we show that if a large crowd is structured in small independent groups, deliberation and social influence within groups improve the crowd's collective accuracy. We asked a live crowd (N=5180) to respond to general-knowledge questions (e.g., what is the height of the Eiffel Tower?). Participants first answered individually, then deliberated and made consensus decisions in groups of five, and finally provided revised individual estimates. We found that averaging consensus decisions was substantially more accurate than aggregating the initial independent opinions. Remarkably, combining as few as four consensus choices outperformed the wisdom of thousands of individuals.
]]></description>
<dc:subject>collective-intelligence wisdom-of-crowds decision-making aggregation algorithms to-write-about metaheuristics social-norms social-engineering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:577489f9a846/</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:wisdom-of-crowds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aggregation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-norms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.02851">
    <title>[1804.02851] Whale swarm algorithm with the mechanism of identifying and escaping from extreme point for multimodal function optimization</title>
    <dc:date>2018-12-11T12:39:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.02851</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Most real-world optimization problems often come with multiple global optima or local optima. Therefore, increasing niching metaheuristic algorithms, which devote to finding multiple optima in a single run, are developed to solve these multimodal optimization problems. However, there are two difficulties urgently to be solved for most existing niching metaheuristic algorithms: how to set the optimal values of niching parameters for different optimization problems, and how to jump out of the local optima efficiently. These two difficulties limited their practicality largely. Based on Whale Swarm Algorithm (WSA) we proposed previously, this paper presents a new multimodal optimizer named WSA with Iterative Counter (WSA-IC) to address these two difficulties. In the one hand, WSA-IC improves the iteration rule of the original WSA for multimodal optimization, which removes the need of specifying different values of attenuation coefficient for different problems to form multiple subpopulations, without introducing any niching parameter. In the other hand, WSA-IC enables the identification of extreme point during iterations relying on two new parameters (i.e., stability threshold Ts and fitness threshold Tf), to jump out of the located extreme point. Moreover, the convergence of WSA-IC is proved. Finally, the proposed WSA-IC is compared with several niching metaheuristic algorithms on CEC2015 niching benchmark test functions and five additional classical multimodal functions with high dimensions. The experimental results demonstrate that WSA-IC statistically outperforms other niching metaheuristic algorithms on most test functions.
]]></description>
<dc:subject>metaheuristics biological-metaphor-of-the-month to-write-about actually rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f6d41d5b886a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biological-metaphor-of-the-month"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:actually"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.03600">
    <title>[1811.03600] Measuring the Effects of Data Parallelism on Neural Network Training</title>
    <dc:date>2018-11-24T20:57:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.03600</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent hardware developments have made unprecedented amounts of data parallelism available for accelerating neural network training. Among the simplest ways to harness next-generation accelerators is to increase the batch size in standard mini-batch neural network training algorithms. In this work, we aim to experimentally characterize the effects of increasing the batch size on training time, as measured in the number of steps necessary to reach a goal out-of-sample error. Eventually, increasing the batch size will no longer reduce the number of training steps required, but the exact relationship between the batch size and how many training steps are necessary is of critical importance to practitioners, researchers, and hardware designers alike. We study how this relationship varies with the training algorithm, model, and data set and find extremely large variation between workloads. Along the way, we reconcile disagreements in the literature on whether batch size affects model quality. Finally, we discuss the implications of our results for efforts to train neural networks much faster in the future.
]]></description>
<dc:subject>machine-learning neural-networks metaheuristics algorithms horse-races batch-learning aggregation-as-painting-yourself-into-a-corner to-write-about to-analogize-away</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ee4a0ad0f743/</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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:batch-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aggregation-as-painting-yourself-into-a-corner"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-analogize-away"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.degruyter.com/view/j/pjbr.2013.4.issue-1/pjbr-2013-0003/pjbr-2013-0003.xml">
    <title>Robot Skill Learning: From Reinforcement Learning to Evolution Strategies : Paladyn, Journal of Behavioral Robotics</title>
    <dc:date>2018-04-02T11:38:41+00:00</dc:date>
    <link>https://www.degruyter.com/view/j/pjbr.2013.4.issue-1/pjbr-2013-0003/pjbr-2013-0003.xml</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Policy improvement methods seek to optimize the parameters of a policy with respect to a utility function. Owing to current trends involving searching in parameter space (rather than action space) and using reward-weighted averaging (rather than gradient estimation), reinforcement learning algorithms for policy improvement, e.g. PoWER and PI2, are now able to learn sophisticated high-dimensional robot skills. A side-effect of these trends has been that, over the last 15 years, reinforcement learning (RL) algorithms have become more and more similar to evolution strategies such as (μW , λ)-ES and CMA-ES. Evolution strategies treat policy improvement as a black-box optimization problem, and thus do not leverage the problem structure, whereas RL algorithms do. In this paper, we demonstrate how two straightforward simplifications to the state-of-the-art RL algorithm PI2 suffice to convert it into the black-box optimization algorithm (μW, λ)-ES. Furthermore, we show that (μW , λ)-ES empirically outperforms PI2 on the tasks in [36]. It is striking that PI2 and (μW , λ)-ES share a common core, and that the simpler algorithm converges faster and leads to similar or lower final costs. We argue that this difference is due to a third trend in robot skill learning: the predominant use of dynamic movement primitives (DMPs). We show how DMPs dramatically simplify the learning problem, and discuss the implications of this for past and future work on policy improvement for robot skill learning

]]></description>
<dc:subject>robotics machine-learning metaheuristics algorithms learning-by-doing engineering-design planning to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d44d476a4be3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robotics"/>
	<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:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-doing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.sciencedirect.com/science/article/abs/pii/S0377221710006211">
    <title>A hybrid placement strategy for the three-dimensional strip packing problem - ScienceDirect</title>
    <dc:date>2018-03-20T12:16:41+00:00</dc:date>
    <link>https://www.sciencedirect.com/science/article/abs/pii/S0377221710006211</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper presents a hybrid placement strategy for the three-dimensional strip packing problem which involves packing a set of cuboids (‘boxes’) into a three-dimensional bin (parallelepiped) of fixed width and height but unconstrained length (the ‘container’). The goal is to pack all of the boxes into the container, minimising its resulting length. This problem has potential industry application in stock cutting (wood, polystyrene, etc. – minimising wastage) and also cargo loading, as well as other applications in areas such as multi-dimensional resource scheduling. In addition to the proposed strategy a number of test results on available literature benchmark problems are presented and analysed. The results of empirical testing of the algorithm show that it out-performs other methods from the literature, consistently in terms of speed and solution quality-producing 28 best known results from 35 test cases.]]></description>
<dc:subject>operations-research hyperheuristics metaheuristics optimization constraint-satisfaction nudge-targets consider:representation consider:looking-to-see to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7a2487aa80f1/</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:hyperheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.01076">
    <title>[1705.01076] An improved Ant Colony System for the Sequential Ordering Problem</title>
    <dc:date>2018-01-15T12:06:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.01076</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[It is not rare that the performance of one metaheuristic algorithm can be improved by incorporating ideas taken from another. In this article we present how Simulated Annealing (SA) can be used to improve the efficiency of the Ant Colony System (ACS) and Enhanced ACS when solving the Sequential Ordering Problem (SOP). Moreover, we show how the very same ideas can be applied to improve the convergence of a dedicated local search, i.e. the SOP-3-exchange algorithm. A statistical analysis of the proposed algorithms both in terms of finding suitable parameter values and the quality of the generated solutions is presented based on a series of computational experiments conducted on SOP instances from the well-known TSPLIB and SOPLIB2006 repositories. The proposed ACS-SA and EACS-SA algorithms often generate solutions of better quality than the ACS and EACS, respectively. Moreover, the EACS-SA algorithm combined with the proposed SOP-3-exchange-SA local search was able to find 10 new best solutions for the SOP instances from the SOPLIB2006 repository, thus improving the state-of-the-art results as known from the literature. Overall, the best known or improved solutions were found in 41 out of 48 cases.
]]></description>
<dc:subject>metaheuristics ACO ant-colony horse-races performance-measure to-write-about that-first-sentence-as-understatement-of-the-year</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:597ce5487c0b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ACO"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ant-colony"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<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:that-first-sentence-as-understatement-of-the-year"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.08835">
    <title>[1702.08835] Deep Forest: Towards An Alternative to Deep Neural Networks</title>
    <dc:date>2017-09-27T11:50:37+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.08835</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we propose gcForest, a decision tree ensemble approach with performance highly competitive to deep neural networks. In contrast to deep neural networks which require great effort in hyper-parameter tuning, gcForest is much easier to train. Actually, even when gcForest is applied to different data from different domains, excellent performance can be achieved by almost same settings of hyper-parameters. The training process of gcForest is efficient and scalable. In our experiments its training time running on a PC is comparable to that of deep neural networks running with GPU facilities, and the efficiency advantage may be more apparent because gcForest is naturally apt to parallel implementation. Furthermore, in contrast to deep neural networks which require large-scale training data, gcForest can work well even when there are only small-scale training data. Moreover, as a tree-based approach, gcForest should be easier for theoretical analysis than deep neural networks.
]]></description>
<dc:subject>via:jason-moore machine-learning architecture metaheuristics to-write-about design-patterns</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:28918ffce86f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:jason-moore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:architecture"/>
	<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:design-patterns"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.05915">
    <title>[1709.05915] Push and Pull Search for Solving Constrained Multi-objective Optimization Problems</title>
    <dc:date>2017-09-25T20:17:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.05915</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper proposes a push and pull search (PPS) framework for solving constrained multi-objective optimization problems (CMOPs). To be more specific, the proposed PPS divides the search process into two different stages, including the push and pull search stages. In the push stage, a multi-objective evolutionary algorithm (MOEA) is adopted to explore the search space without considering any constraints, which can help to get across infeasible regions very fast and approach the unconstrained Pareto front. Furthermore, the landscape of CMOPs with constraints can be probed and estimated in the push stage, which can be utilized to conduct the parameters setting for constraint-handling approaches applied in the pull stage. Then, a constrained multi-objective evolutionary algorithm (CMOEA) equipped with an improved epsilon constraint-handling is applied to pull the infeasible individuals achieved in the push stage to the feasible and non-dominated regions. Compared with other CMOEAs, the proposed PPS method can more efficiently get across infeasible regions and converge to the feasible and non-dominated regions by applying push and pull search strategies at different stages. To evaluate the performance regarding convergence and diversity, a set of benchmark CMOPs is used to test the proposed PPS and compare with other five CMOEAs, including MOEA/D-CDP, MOEA/D-SR, C-MOEA/D, MOEA/D-Epsilon and MOEA/D-IEpsilon. The comprehensive experimental results demonstrate that the proposed PPS achieves significantly better or competitive performance than the other five CMOEAs on most of the benchmark set.
]]></description>
<dc:subject>hey-I-know-this-guy multiobjective-optimization metaheuristics evolutionary-algorithms algorithms to-write-about nudge-targets consider:implementing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:638a09114b89/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:implementing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1708.01625">
    <title>[1708.01625] Traffic flow optimization using a quantum annealer</title>
    <dc:date>2017-09-24T13:16:38+00:00</dc:date>
    <link>https://arxiv.org/abs/1708.01625</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Quantum annealing algorithms belong to the class of meta-heuristic tools, applicable for solving binary optimization problems. Hardware implementations of quantum annealing, such as the quantum processing units (QPUs) produced by D-Wave Systems, have been subject to multiple analyses in research, with the aim of characterizing the technology's usefulness for optimization and sampling tasks. In this paper, we present a real-world application that uses quantum technologies. Specifically, we show how to map certain parts of the real-world traffic flow optimization problem to be suitable for quantum annealing. We show that time-critical optimization tasks, such as continuous redistribution of position data for cars in dense road networks, are suitable candidates for quantum applications. Due to the limited size and connectivity of current-generation D-Wave QPUs, we use a hybrid quantum and classical approach to solve the traffic flow problem.
]]></description>
<dc:subject>metaheuristics optimization to-understand to-write-about quantums</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d5a4dbbee707/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<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:quantums"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1504.04909">
    <title>[1504.04909] Illuminating search spaces by mapping elites</title>
    <dc:date>2017-09-14T11:22:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1504.04909</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search for stronger, cheaper, safer designs, scientists search for models that best explain data, etc. The goal of search algorithms has traditionally been to return the single highest-performing solution in a search space. Here we describe a new, fundamentally different type of algorithm that is more useful because it provides a holistic view of how high-performing solutions are distributed throughout a search space. It creates a map of high-performing solutions at each point in a space defined by dimensions of variation that a user gets to choose. This Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) algorithm illuminates search spaces, allowing researchers to understand how interesting attributes of solutions combine to affect performance, either positively or, equally of interest, negatively. For example, a drug company may wish to understand how performance changes as the size of molecules and their cost-to-produce vary. MAP-Elites produces a large diversity of high-performing, yet qualitatively different solutions, which can be more helpful than a single, high-performing solution. Interestingly, because MAP-Elites explores more of the search space, it also tends to find a better overall solution than state-of-the-art search algorithms. We demonstrate the benefits of this new algorithm in three different problem domains ranging from producing modular neural networks to designing simulated and real soft robots. Because MAP- Elites (1) illuminates the relationship between performance and dimensions of interest in solutions, (2) returns a set of high-performing, yet diverse solutions, and (3) improves finding a single, best solution, it will advance science and engineering.
]]></description>
<dc:subject>hey-I-know-this-guy metaheuristics fitness-landscapes feature-selection to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6bfb5cca912e/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1708.00214">
    <title>[1708.00214] Natural Language Processing with Small Feed-Forward Networks</title>
    <dc:date>2017-08-05T11:30:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1708.00214</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We show that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models. Motivated by resource-constrained environments like mobile phones, we showcase simple techniques for obtaining such small neural network models, and investigate different tradeoffs when deciding how to allocate a small memory budget.
]]></description>
<dc:subject>neural-networks natural-language-processing machine-learning amusing not-so-deep to-write-about metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:22799e319e69/</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:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:not-so-deep"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.10201">
    <title>[1705.10201] Machine Learned Learning Machines</title>
    <dc:date>2017-07-21T13:23:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.10201</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. Though these are methods that typically operate separately, we combine evolutionary adaptation and machine learning into one approach. Our focus is on machines that can learn during their lifetime, but instead of equipping them with a machine learning algorithm we aim to let them evolve their ability to learn by themselves. We use evolvable networks of probabilistic and deterministic logic gates, known as Markov Brains, as our computational model organism. The ability of Markov Brains to learn is augmented by a novel adaptive component that can change its computational behavior based on feedback. We show that Markov Brains can indeed evolve to incorporate these feedback gates to improve their adaptability to variable environments. By combining these two methods, we now also implemented a computational model that can be used to study the evolution of learning.
]]></description>
<dc:subject>hey-I-know-this-person machine-learning local evolutionary-algorithms metaheuristics to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:229329e3c9ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-person"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:local"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1706.04119">
    <title>[1706.04119] From MEGATON to RASCAL: Surfing the Parameter Space of Evolutionary Algorithms</title>
    <dc:date>2017-06-20T17:14:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1706.04119</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The practice of evolutionary algorithms involves a mundane yet inescapable phase, namely, finding parameters that work well. How big should the population be? How many generations should the algorithm run? What is the (tournament selection) tournament size? What probabilities should one assign to crossover and mutation? All these nagging questions need good answers if one is to embrace success. Through an extensive series of experiments over multiple evolutionary algorithm implementations and problems we show that parameter space tends to be rife with viable parameters. We aver that this renders the life of the practitioner that much easier, and cap off our study with an advisory digest for the weary.
]]></description>
<dc:subject>hey-I-know-this-guy machine-learning meta-optimization evolutionary-algorithms metaheuristics hyperheuristics to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fcd9c47b435e/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meta-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hyperheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.00853">
    <title>[1704.00853] A History of Metaheuristics</title>
    <dc:date>2017-04-27T11:30:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.00853</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This chapter describes the history of metaheuristics in five distinct periods, starting long before the first use of the term and ending a long time in the future.
]]></description>
<dc:subject>metaheuristics history history-of-engineering to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:577a560ecc36/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:history"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:history-of-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.07929">
    <title>[1703.07929] Diversification-Based Learning in Computing and Optimization</title>
    <dc:date>2017-04-27T11:25:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.07929</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Diversification-Based Learning (DBL) derives from a collection of principles and methods introduced in the field of metaheuristics that have broad applications in computing and optimization. We show that the DBL framework goes significantly beyond that of the more recent Opposition-based learning (OBL) framework introduced in Tizhoosh (2005), which has become the focus of numerous research initiatives in machine learning and metaheuristic optimization. We unify and extend earlier proposals in metaheuristic search (Glover, 1997, Glover and Laguna, 1997) to give a collection of approaches that are more flexible and comprehensive than OBL for creating intensification and diversification strategies in metaheuristic search. We also describe potential applications of DBL to various subfields of machine learning and optimization.
]]></description>
<dc:subject>metaheuristics coevolution to-write-about system-of-professions artificial-intelligence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8dec26ed5b8f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coevolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>