<?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/2503.07811"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/journals/philosophy-of-science/article/navigating-in-the-dark/C02547A095F27160DE525E3B3FDA25CE?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Issues"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2006.00840"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.04900"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s10710-021-09400-0"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2005.12244"/>
	<rdf:li rdf:resource="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3250568/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.00382"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.06660"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/10.1101/2020.05.26.116848v1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.04087"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.06853"/>
	<rdf:li rdf:resource="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0216125"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1511.05219"/>
	<rdf:li rdf:resource="https://www.sciencedirect.com/science/article/abs/pii/S0196677498909889"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.10038"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1506.08415"/>
	<rdf:li rdf:resource="http://blog.mrmeyer.com/2019/all-learning-is-modeling-my-five-minute-talk-at-cime2019-that-made-things-weird/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1101.0891"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.02045"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.08162"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.10489"/>
	<rdf:li rdf:resource="https://www.jstatsoft.org/article/view/v016i09"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/early/2018/08/09/1802407115"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/srep34175"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.00548"/>
	<rdf:li rdf:resource="https://scholar.google.com/scholar?q=jensen+cohen+multiple+comparisons"/>
	<rdf:li rdf:resource="https://christophm.github.io/interpretable-ml-book/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1712.00180"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.04380"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.06960"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.01129"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1603.02597"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.07681"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.00479"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1612.08699"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1602.01241"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.08617"/>
	<rdf:li rdf:resource="https://tedunderwood.com/2017/07/13/were-probably-due-for-another-discussion-of-stanley-fish/"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.08085"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1011.4245"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1609.08312"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1501.01300"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2017/03/04/113720?rss=1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.05571"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.06336"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.07306"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1105.6344#"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/astro-ph/0301491"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.01331"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.07667"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.04917"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.03230"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.02707"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.06096"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.03757"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1610.08910"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1612.01605"/>
	<rdf:li rdf:resource="https://www.researchgate.net/publication/256388072_Modeling_Cognition_How_Fiction_Relates_to_Fact"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.06168"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.07312"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.05923"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.07705"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1606.07207"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/26/055624"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1604.02008"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.02765"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.01441"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.1132"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/2503.07811">
    <title>[2503.07811] A primer on optimal transport for causal inference with observational data</title>
    <dc:date>2025-04-05T22:00:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2503.07811</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The theory of optimal transportation has developed into a powerful and elegant framework for comparing probability distributions, with wide-ranging applications in all areas of science. The fundamental idea of analyzing probabilities by comparing their underlying state space naturally aligns with the core idea of causal inference, where understanding and quantifying counterfactual states is paramount. Despite this intuitive connection, explicit research at the intersection of optimal transport and causal inference is only beginning to develop. Yet, many foundational models in causal inference have implicitly relied on optimal transport principles for decades, without recognizing the underlying connection. Therefore, the goal of this review is to offer an introduction to the surprisingly deep existing connections between optimal transport and the identification of causal effects with observational data -- where optimal transport is not just a set of potential tools, but actually builds the foundation of model assumptions. As a result, this review is intended to unify the language and notation between different areas of statistics, mathematics, and econometrics, by pointing out these existing connections, and to explore novel problems and directions for future work in both areas derived from this realization.
]]></description>
<dc:subject>probability-theory optimal-transport causal-inference inference to-understand via:? modeling machine-learning numerical-methods</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:28573aa6a3a3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimal-transport"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:causal-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/journals/philosophy-of-science/article/navigating-in-the-dark/C02547A095F27160DE525E3B3FDA25CE?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Issues">
    <title>Navigating in the Dark | Philosophy of Science | Cambridge Core</title>
    <dc:date>2025-03-31T13:51:03+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/philosophy-of-science/article/navigating-in-the-dark/C02547A095F27160DE525E3B3FDA25CE?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Issues</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This article introduces the snap hook methodology, a method used notably in astrochemistry as a way to indirectly validate and assess the accuracy of computational calculations in the absence of experimental or observational data. We argue that this methodology has tremendous potential for all computationally intensive scientific fields as a substitute for traditional verification and validation standards when those are not accessible and estimating the reliability of numerical predictions becomes a real difficulty. The goal of this article is to give to this method, which seems to be implicitly relied upon in many areas, a proper formulation, in order for philosophers of science to enter the debate and to highlight its undeniable potential in terms of interdisciplinary facilitation and knowledge transmission.

]]></description>
<dc:subject>to-understand via-? models-and-modes modeling science-from-a-distance looking-to-see looking-to-guess-better rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:58af6d1d35e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via-?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:science-from-a-distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-guess-better"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2006.00840">
    <title>[2006.00840] Universal Robust Regression via Maximum Mean Discrepancy</title>
    <dc:date>2024-08-02T11:23:25+00:00</dc:date>
    <link>https://arxiv.org/abs/2006.00840</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Many modern datasets are collected automatically and are thus easily contaminated by outliers. This led to a regain of interest in robust estimation, including new notions of robustness such as robustness to adversarial contamination of the data. However, most robust estimation methods are designed for a specific model. Notably, many methods were proposed recently to obtain robust estimators in linear models (or generalized linear models), and a few were developed for very specific settings, for example beta regression or sample selection models. In this paper we develop a new approach for robust estimation in arbitrary regression models, based on Maximum Mean Discrepancy minimization. We build two estimators which are both proven to be robust to Huber-type contamination. We obtain a non-asymptotic error bound for one them and show that it is also robust to adversarial contamination, but this estimator is computationally more expensive to use in practice than the other one. As a by-product of our theoretical analysis of the proposed estimators we derive new results on kernel conditional mean embedding of distributions which are of independent interest.
]]></description>
<dc:subject>statistics modeling robustness discrepancy-theory MMD heuristics rather-interesting to-understand to-learn consider:symbolic-regression consider:Pareto-GP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1e134d490a13/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrepancy-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:MMD"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<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-learn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:Pareto-GP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.04900">
    <title>[2106.04900] Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks</title>
    <dc:date>2022-07-09T12:40:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.04900</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Continuum mechanics simulators, numerically solving one or more partial differential equations, are essential tools in many areas of science and engineering, but their performance often limits application in practice. Recent modern machine learning approaches have demonstrated their ability to accelerate spatio-temporal predictions, although, with only moderate accuracy in comparison. Here we introduce MultiScaleGNN, a novel multi-scale graph neural network model for learning to infer unsteady continuum mechanics. MultiScaleGNN represents the physical domain as an unstructured set of nodes, and it constructs one or more graphs, each of them encoding different scales of spatial resolution. Successive learnt message passing between these graphs improves the ability of GNNs to capture and forecast the system state in problems encompassing a range of length scales. Using graph representations, MultiScaleGNN can impose periodic boundary conditions as an inductive bias on the edges in the graphs, and achieve independence to the nodes' positions. We demonstrate this method on advection problems and incompressible fluid dynamics. Our results show that the proposed model can generalise from uniform advection fields to high-gradient fields on complex domains at test time and infer long-term Navier-Stokes solutions within a range of Reynolds numbers. Simulations obtained with MultiScaleGNN are between two and four orders of magnitude faster than the ones on which it was trained.
]]></description>
<dc:subject>modeling approximation machine-learning neural-networks 20-years-ago-we-did-this-in-GP to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d2886cc4e68b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:20-years-ago-we-did-this-in-GP"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s10710-021-09400-0">
    <title>Symbolic-regression boosting | SpringerLink</title>
    <dc:date>2021-07-22T10:37:57+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s10710-021-09400-0</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Modifying standard gradient boosting by replacing the embedded weak learner in favor of a strong(er) one, we present SyRBo: symbolic-regression boosting. Experiments over 98 regression datasets show that by adding a small number of boosting stages—between 2 and 5—to a symbolic regressor, statistically significant improvements can often be attained. We note that coding SyRBo on top of any symbolic regressor is straightforward, and the added cost is simply a few more evolutionary rounds. SyRBo is essentially a simple add-on that can be readily added to an extant symbolic regressor, often with beneficial results.

]]></description>
<dc:subject>hey-I-know-this-guy symbolic-regression modeling rather-interesting to-write-about algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d0cbca143b4b/</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:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2005.12244">
    <title>[2005.12244] Controllability of Hypergraphs</title>
    <dc:date>2021-05-23T11:54:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2005.12244</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we develop a notion of controllability for hypergraphs via tensor algebra and polynomial control theory. Inspired by uniform hypergraphs, we propose a new tensor-based multilinear dynamical system representation, and derive a Kalman-rank-like condition to determine the minimum number of control nodes (MCN) needed to achieve controllability of even uniform hypergraphs. We present an efficient heuristic to obtain the MCN. MCN can be used as a measure of robustness, and we show that it is related to the hypergraph degree distribution in simulated examples. Finally, we use MCN to examine robustness in real biological networks.
]]></description>
<dc:subject>hypergraphs control-theory modeling rather-interesting define-your-terms to-write-about an-example-would-be-good-about-now consider:visualization consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d5159995b05d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:an-example-would-be-good-about-now"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3250568/">
    <title>Probability Machines: Consistent Probability Estimation Using Nonparametric Learning Machines</title>
    <dc:date>2021-05-22T11:27:00+00:00</dc:date>
    <link>https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3250568/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Most machine learning approaches only provide a classification for binary responses. However, probabilities are required for risk estimation using individual patient characteristics. It has been shown recently that every statistical learning machine known to be consistent for a nonparametric regression problem is a probability machine that is provably consistent for this estimation problem.

]]></description>
<dc:subject>via:GPTP machine-learning statistics modeling representation probability-theory to-write-about to-visualize classification</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e98d77ff6c6e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:GPTP"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.00382">
    <title>[1808.00382] Reassembling the English novel, 1789-1919</title>
    <dc:date>2020-11-08T12:33:14+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.00382</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The absence of an exhaustive bibliography of novels published in the British Isles and Ireland during the 19th century blocks several lines of research in sociologically-inclined literary history and book history. Without a detailed account of novelistic production, it is difficult to characterize, for example, the population of individuals who pursued careers as novelists. This paper contributes to efforts to develop such an account by estimating yearly rates of new novel publication in the British Isles and Ireland between 1789 and 1919. This period witnessed, in aggregate, the publication of between 40,000 and 63,000 previously unpublished novels. The number of new novels published each year counts as essential information for researchers interested in understanding the development of the text industry between 1789 and 1919.
]]></description>
<dc:subject>digital-humanities modeling rather-interesting inference missing-mass-problems regression to-understand consider:empirical-fit</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5094453a37fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:missing-mass-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:empirical-fit"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.06660">
    <title>[1802.06660] Linear Equations with Ordered Data</title>
    <dc:date>2020-06-13T21:27:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.06660</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Following a recently considered generalization of linear equations to unordered data vectors, we perform a further generalization to ordered data vectors. These generalized equations naturally appear in the analysis of vector addition systems (or Petri nets) extended with ordered data. We show that nonnegative-integer solvability of linear equations is computationally equivalent (up to an exponential blowup) with the reachability problem for (plain) vector addition systems. This high complexity is surprising, and contrasts with NP-completeness for unordered data vectors. Also surprisingly, we achieve polynomial time complexity of the solvability problem when the nonnegative-integer restriction on solutions is dropped.
]]></description>
<dc:subject>representation modeling rather-interesting to-understand to-simulate consider:applications</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8d60aca0ebce/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:applications"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/10.1101/2020.05.26.116848v1">
    <title>Deciphering trophic interactions in a mid-Cambrian assemblage | bioRxiv</title>
    <dc:date>2020-05-29T11:47:03+00:00</dc:date>
    <link>https://www.biorxiv.org/content/10.1101/2020.05.26.116848v1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The Cambrian Period (541-485 Mya) represents a major stage in the development of metazoan-dominated assemblages with complex community structure and species interactions. Exceptionally preserved fossil sites have allowed specimen-based identification of putative trophic interactions to which network analyses have been applied. However, network analyses of the fossil record suffer from incomplete and indirect data, time averaging that obscures species coexistence, and biases in preservation. Here, we present a novel high-resolution fossil dataset from the Raymond Quarry (RQ) member of the mid-Cambrian Burgess Shale (7549 specimens, 61 taxa, ~510 Mya) affording new perspectives on these challenging issues. Further, we formulate a new measure of 'preservation bias' that aids identification of those assemblage subsets to which network analyses can be reliably applied. For sections with sufficiently low bias, abundance correlation network analyses predicted longitudinally consistent trophic and competitive interactions. Our correlation network analyses predicted previously postulated trophic interactions with 83.5% accuracy and demonstrated a shift from specialist interaction-dominated assemblages to ones dominated by generalist and competitive interactions. This approach provides a robust, taphonomically corrected framework to explore and predict in detail the existence and ecological character of putative interactions in fossil datasets, offering new windows on ancient food-webs.

]]></description>
<dc:subject>ecosystems modeling paleontology rather-interesting theoretical-biology statistics fossils inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e98c10f30570/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ecosystems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:paleontology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fossils"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.04087">
    <title>[1801.04087] Gene regulatory network inference: an introductory survey</title>
    <dc:date>2020-05-23T13:23:17+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.04087</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Gene regulatory networks are powerful abstractions of biological systems. Since the advent of high-throughput measurement technologies in biology in the late 90s, reconstructing the structure of such networks has been a central computational problem in systems biology. While the problem is certainly not solved in its entirety, considerable progress has been made in the last two decades, with mature tools now available. This chapter aims to provide an introduction to the basic concepts underpinning network inference tools, attempting a categorisation which highlights commonalities and relative strengths. While the chapter is meant to be self-contained, the material presented should provide a useful background to the later, more specialised chapters of this book.
]]></description>
<dc:subject>gene-regulatory-networks inverse-problems bioinformatics systems-biology rather-interesting modeling to-write-about to-simulate consider:data-quality consider:representation consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3c46f24714c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:data-quality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<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/1801.06853">
    <title>[1801.06853] Basic Model of Purposeful Kinesis</title>
    <dc:date>2020-05-02T15:44:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.06853</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The notions of taxis and kinesis are introduced and used to describe two types of behavior of an organism in non-uniform conditions: (i) Taxis means the guided movement to more favorable conditions; (ii) Kinesis is the non-directional change in space motion in response to the change of conditions. Migration and dispersal of animals has evolved under control of natural selection. In a simple formalisation, the strategy of dispersal should increase Darwinian fitness. We introduce new models of purposeful kinesis with diffusion coefficient dependent on fitness. The local and instant evaluation of Darwinian fitness is used, the reproduction coefficient. New models include one additional parameter, intensity of kinesis, and may be considered as the {\em minimal models of purposeful kinesis}. The properties of models are explored by a series of numerical experiments. It is demonstrated how kinesis could be beneficial for assimilation of patches of food or of periodic fluctuations. Kinesis based on local and instant estimations of fitness is not always beneficial: for species with the Allee effect it can delay invasion and spreading. It is proven that kinesis cannot modify stability of positive homogeneous steady states.
]]></description>
<dc:subject>theoretical-biology ethology rather-interesting animal-behavior agents statistics modeling to-simulate to-write-about artificial-life</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bf23578e4341/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ethology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:animal-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:agents"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:artificial-life"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0216125">
    <title>Scientific discovery in a model-centric framework: Reproducibility, innovation, and epistemic diversity</title>
    <dc:date>2020-05-02T14:48:00+00:00</dc:date>
    <link>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0216125</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Consistent confirmations obtained independently of each other lend credibility to a scientific result. We refer to results satisfying this consistency as reproducible and assume that reproducibility is a desirable property of scientific discovery. Yet seemingly science also progresses despite irreproducible results, indicating that the relationship between reproducibility and other desirable properties of scientific discovery is not well understood. These properties include early discovery of truth, persistence on truth once it is discovered, and time spent on truth in a long-term scientific inquiry. We build a mathematical model of scientific discovery that presents a viable framework to study its desirable properties including reproducibility. In this framework, we assume that scientists adopt a model-centric approach to discover the true model generating data in a stochastic process of scientific discovery. We analyze the properties of this process using Markov chain theory, Monte Carlo methods, and agent-based modeling. We show that the scientific process may not converge to truth even if scientific results are reproducible and that irreproducible results do not necessarily imply untrue results. The proportion of different research strategies represented in the scientific population, scientists’ choice of methodology, the complexity of truth, and the strength of signal contribute to this counter-intuitive finding. Important insights include that innovative research speeds up the discovery of scientific truth by facilitating the exploration of model space and epistemic diversity optimizes across desirable properties of scientific discovery.

]]></description>
<dc:subject>modeling symbolic-regression machine-learning rather-interesting reinventing-the-wheel Pareto-GP to-write-about consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bb816f338356/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinventing-the-wheel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Pareto-GP"/>
	<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/1511.05219">
    <title>[1511.05219] How much does your data exploration overfit? Controlling bias via information usage</title>
    <dc:date>2020-05-02T11:28:36+00:00</dc:date>
    <link>https://arxiv.org/abs/1511.05219</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Modern data is messy and high-dimensional, and it is often not clear a priori what are the right questions to ask. Instead, the analyst typically needs to use the data to search for interesting analyses to perform and hypotheses to test. This is an adaptive process, where the choice of analysis to be performed next depends on the results of the previous analyses on the same data. Ultimately, which results are reported can be heavily influenced by the data. It is widely recognized that this process, even if well-intentioned, can lead to biases and false discoveries, contributing to the crisis of reproducibility in science. But while %the adaptive nature of exploration any data-exploration renders standard statistical theory invalid, experience suggests that different types of exploratory analysis can lead to disparate levels of bias, and the degree of bias also depends on the particulars of the data set. In this paper, we propose a general information usage framework to quantify and provably bound the bias and other error metrics of an arbitrary exploratory analysis. We prove that our mutual information based bound is tight in natural settings, and then use it to give rigorous insights into when commonly used procedures do or do not lead to substantially biased estimation. Through the lens of information usage, we analyze the bias of specific exploration procedures such as filtering, rank selection and clustering. Our general framework also naturally motivates randomization techniques that provably reduces exploration bias while preserving the utility of the data analysis. We discuss the connections between our approach and related ideas from differential privacy and blinded data analysis, and supplement our results with illustrative simulations.
]]></description>
<dc:subject>overfitting machine-learning bias statistics information-theory modeling to-understand via:several to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e5ccae7dfdab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:overfitting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bias"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:several"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.sciencedirect.com/science/article/abs/pii/S0196677498909889">
    <title>Data Structures for Mobile Data - ScienceDirect</title>
    <dc:date>2020-03-08T19:06:30+00:00</dc:date>
    <link>https://www.sciencedirect.com/science/article/abs/pii/S0196677498909889</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Akinetic data structure(KDS) maintains an attribute of interest in a system of geometric objects undergoing continuous motion. In this paper we develop a concentual framework for kinetic data structures, we propose a number of criteria for the quality of such structures, and we describe a number of fundamental techniques for their design. We illustrate these general concepts by presenting kinetic data structures for maintaining the convex hull and the closest pair of moving points in the plane; these structures behave well according to the proposed quality criteria for KDSs.]]></description>
<dc:subject>data-structures rather-interesting to-simulate to-write-about consider:processing-sims modeling dynamical-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:71d465109b7d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-structures"/>
	<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:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:processing-sims"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.10038">
    <title>[1802.10038] Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning</title>
    <dc:date>2020-01-26T13:51:59+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.10038</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models) instead of starting the training from scratch. (2) Performing cross fold training on a single set of ground truth data (line images and their transcriptions) with a single OCR engine (OCRopus) produces a committee whose members then vote for the best outcome by also taking the top-N alternatives and their intrinsic confidence values into account. (3) Following the principle of maximal disagreement we select additional training lines which the voters disagree most on, expecting them to offer the highest information gain for a subsequent training (active learning). Evaluations on six early printed books yielded the following results: On average the combination of pretraining and voting improved the character accuracy by 46% when training five folds starting from the same mixed model. This number rose to 53% when using different models for pretraining, underlining the importance of diverse voters. Incorporating active learning improved the obtained results by another 16% on average (evaluated on three of the six books). Overall, the proposed methods lead to an average error rate of 2.5% when training on only 60 lines. Using a substantial ground truth pool of 1,000 lines brought the error rate down even further to less than 1% on average.
]]></description>
<dc:subject>OCR digital-humanities digitization text-processing image-processing machine-learning data-cleaning the-mangle-in-practice modeling rather-interesting to-write-about to-simulate consider:stochastic-resonance</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c2645c071b01/</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:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digitization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-processing"/>
	<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:data-cleaning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-mangle-in-practice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:stochastic-resonance"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1506.08415">
    <title>[1506.08415] PLG2: Multiperspective Processes Randomization and Simulation for Online and Offline Settings</title>
    <dc:date>2019-07-25T11:17:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1506.08415</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Process mining represents an important field in BPM and data mining research. Recently, it has gained importance also for practitioners: more and more companies are creating business process intelligence solutions. The evaluation of process mining algorithms requires, as any other data mining task, the availability of large amount of real-world data. Despite the increasing availability of such datasets, they are affected by many limitations, in primis the absence of a "gold standard" (i.e., the reference model). 
This paper extends an approach, already available in the literature, for the generation of random processes. Novelties have been introduced throughout the work and, in particular, they involve the complete support for multiperspective models and logs (i.e., the control-flow perspective is enriched with time and data information) and for online settings (i.e., generation of multiperspective event streams and concept drifts). The proposed new framework is able to almost entirely cover the spectrum of possible scenarios that can be observed in the real-world. The proposed approach is implemented as a publicly available Java application, with a set of APIs for the programmatic execution of experiments.
]]></description>
<dc:subject>process-mining learning-by-watching machine-learning statistics modeling dynamical-systems what-gets-measured to-write-about representation discrete-event-simulators to-simulate time-series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:122986d87d39/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:process-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:what-gets-measured"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrete-event-simulators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.mrmeyer.com/2019/all-learning-is-modeling-my-five-minute-talk-at-cime2019-that-made-things-weird/">
    <title>All Learning Is Modeling: My Five-Minute Talk at #CIME2019 That Made Things Weird – dy/dan</title>
    <dc:date>2019-03-21T11:39:32+00:00</dc:date>
    <link>http://blog.mrmeyer.com/2019/all-learning-is-modeling-my-five-minute-talk-at-cime2019-that-made-things-weird/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[I contributed to a panel on mathematical modeling panel at MSRI this week – five minutes of prepared remarks and then answers to a couple of questions.

Sol Garfunkel, a co-panelist and personal hero, would later call my introductory remarks “completely wrong.” A university professor called them “dangerous.”

I mention those reviews not to marshal sympathy. I’m really happy with my remarks and I don’t think I was misunderstood! I’m mentioning them to acknowledge that my remarks caused a lot of anxiety among people who call themselves mathematical modelers. I’ll respond to some of those anxieties below.

]]></description>
<dc:subject>models-and-modes modeling essay yes to-write-about empathy define-your-terms system-of-professions formalization deformalization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0b3340ca8698/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:essay"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:yes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:empathy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deformalization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1101.0891">
    <title>[1101.0891] To Explain or to Predict?</title>
    <dc:date>2019-03-03T13:39:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1101.0891</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description. In many disciplines there is near-exclusive use of statistical modeling for causal explanation and the assumption that models with high explanatory power are inherently of high predictive power. Conflation between explanation and prediction is common, yet the distinction must be understood for progressing scientific knowledge. While this distinction has been recognized in the philosophy of science, the statistical literature lacks a thorough discussion of the many differences that arise in the process of modeling for an explanatory versus a predictive goal. The purpose of this article is to clarify the distinction between explanatory and predictive modeling, to discuss its sources, and to reveal the practical implications of the distinction to each step in the modeling process.
]]></description>
<dc:subject>modeling modeling-is-not-mathematics statistics prediction interpretability interestingness (they-forgot-that-one) philosophy-of-science multiobjective-optimization to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3abf85660a41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interestingness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:(they-forgot-that-one)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<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/1804.02045">
    <title>[1804.02045] Approximating Functions on Boxes</title>
    <dc:date>2019-02-22T23:08:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.02045</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The vector space of all polynomial functions of degree k on a box of dimension n is of dimension (nk). A consequence of this fact is that a function can be approximated on vertices of the box using other vertices to higher degrees than expected. This approximation is useful for various biological applications such as predicting the effect of a treatment with drug combinations and computing values of fitness landscape.]]></description>
<dc:subject>approximation fitness-landscapes dimension-reduction rather-interesting statistics modeling bioinformatics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:319a7d7a9e80/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.08162">
    <title>[1901.08162] Causal Reasoning from Meta-reinforcement Learning</title>
    <dc:date>2019-01-25T10:56:29+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.08162</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal structure. We find that the trained agent can perform causal reasoning in novel situations in order to obtain rewards. The agent can select informative interventions, draw causal inferences from observational data, and make counterfactual predictions. Although established formal causal reasoning algorithms also exist, in this paper we show that such reasoning can arise from model-free reinforcement learning, and suggest that causal reasoning in complex settings may benefit from the more end-to-end learning-based approaches presented here. This work also offers new strategies for structured exploration in reinforcement learning, by providing agents with the ability to perform -- and interpret -- experiments.
]]></description>
<dc:subject>causality modeling machine-learning reinforcement-learning side-effects to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3f4e539259f5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinforcement-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:side-effects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.10489">
    <title>[1807.10489] Randomized residual-based error estimators for parametrized equations</title>
    <dc:date>2018-11-04T13:01:33+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.10489</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a randomized a posteriori error estimator for reduced order approximations of parametrized (partial) differential equations. The error estimator has several important properties: the effectivity is close to unity with prescribed lower and upper bounds at specified high probability; the estimator does not require the calculation of stability (coercivity, or inf-sup) constants; the online cost to evaluate the a posteriori error estimator is commensurate with the cost to find the reduced order approximation; the probabilistic bounds extend to many queries with only modest increase in cost. To build this estimator, we first estimate the norm of the error with a Monte-Carlo estimator using Gaussian random vectors whose covariance is chosen according to the desired error measure, e.g. user-defined norms or quantity of interest. Then, we introduce a dual problem with random right-hand side the solution of which allows us to rewrite the error estimator in terms of the residual of the original equation. In order to have a fast-to-evaluate estimator, model order reduction methods can be used to approximate the random dual solutions. Here, we propose a greedy algorithm that is guided by a scalar quantity of interest depending on the error estimator. Numerical experiments on a multi-parametric Helmholtz problem demonstrate that this strategy yields rather low-dimensional reduced dual spaces.
]]></description>
<dc:subject>numerical-methods approximation rather-interesting to-understand modeling algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3e262e6d8dd1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<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:modeling"/>
	<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://www.jstatsoft.org/article/view/v016i09">
    <title>Object-oriented Computation of Sandwich Estimators | Zeileis | Journal of Statistical Software</title>
    <dc:date>2018-10-27T12:14:31+00:00</dc:date>
    <link>https://www.jstatsoft.org/article/view/v016i09</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Sandwich covariance matrix estimators are a popular tool in applied regression modeling for performing inference that is robust to certain types of model misspecification. Suitable implementations are available in the R system for statistical computing for certain model fitting functions only (in particular lm()), but not for other standard regression functions, such as glm(), nls(), or survreg(). Therefore, conceptual tools and their translation to computational tools in the package sandwich are discussed, enabling the computation of sandwich estimators in general parametric models. Object orientation can be achieved by providing a few extractor functions' most importantly for the empirical estimating functions' from which various types of sandwich estimators can be computed.
]]></description>
<dc:subject>via:cshalizi to-understand statistics estimation algorithms programming regression error-measures modeling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3a3e726b45f4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:error-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/early/2018/08/09/1802407115">
    <title>How intermittent breaks in interaction improve collective intelligence | PNAS</title>
    <dc:date>2018-08-25T12:02:50+00:00</dc:date>
    <link>http://www.pnas.org/content/early/2018/08/09/1802407115</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[People influence each other when they interact to solve problems. Such social influence introduces both benefits (higher average solution quality due to exploitation of existing answers through social learning) and costs (lower maximum solution quality due to a reduction in individual exploration for novel answers) relative to independent problem solving. In contrast to prior work, which has focused on how the presence and network structure of social influence affect performance, here we investigate the effects of time. We show that when social influence is intermittent it provides the benefits of constant social influence without the costs. Human subjects solved the canonical traveling salesperson problem in groups of three, randomized into treatments with constant social influence, intermittent social influence, or no social influence. Groups in the intermittent social-influence treatment found the optimum solution frequently (like groups without influence) but had a high mean performance (like groups with constant influence); they learned from each other, while maintaining a high level of exploration. Solutions improved most on rounds with social influence after a period of separation. We also show that storing subjects’ best solutions so that they could be reloaded and possibly modified in subsequent rounds—a ubiquitous feature of personal productivity software—is similar to constant social influence: It increases mean performance but decreases exploration.

]]></description>
<dc:subject>attention psychology wisdom-of-crowds might-it-be-distraction? modeling exploration-and-exploitation learning-by-watching</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:afd58c6be158/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:attention"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wisdom-of-crowds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:might-it-be-distraction?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration-and-exploitation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nature.com/articles/srep34175">
    <title>Three representations of the Ising model | Scientific Reports</title>
    <dc:date>2018-04-02T11:52:19+00:00</dc:date>
    <link>https://www.nature.com/articles/srep34175</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Statistical models that analyse (pairwise) relations between variables encompass assumptions about the underlying mechanism that generated the associations in the observed data. In the present paper we demonstrate that three Ising model representations exist that, although each proposes a distinct theoretical explanation for the observed associations, are mathematically equivalent. This equivalence allows the researcher to interpret the results of one model in three different ways. We illustrate the ramifications of this by discussing concepts that are conceived as problematic in their traditional explanation, yet when interpreted in the context of another explanation make immediate sense.]]></description>
<dc:subject>representation modeling philosophy-of-science rather-interesting to-write-about demonstrations-of-the-mangle</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:efdb75a333ab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<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:demonstrations-of-the-mangle"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.00548">
    <title>[1801.00548] A Machine Learning Approach to Adaptive Covariance Localization</title>
    <dc:date>2018-03-10T13:34:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.00548</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Data assimilation plays a key role in large-scale atmospheric weather forecasting, where the state of the physical system is estimated from model outputs and observations, and is then used as initial condition to produce accurate future forecasts. The Ensemble Kalman Filter (EnKF) provides a practical implementation of the statistical solution of the data assimilation problem and has gained wide popularity as. This success can be attributed to its simple formulation and ease of implementation. EnKF is a Monte-Carlo algorithm that solves the data assimilation problem by sampling the probability distributions involved in Bayes theorem. Because of this, all flavors of EnKF are fundamentally prone to sampling errors when the ensemble size is small. In typical weather forecasting applications, the model state space has dimension 109−1012, while the ensemble size typically ranges between 30−100 members. Sampling errors manifest themselves as long-range spurious correlations and have been shown to cause filter divergence. To alleviate this effect covariance localization dampens spurious correlations between state variables located at a large distance in the physical space, via an empirical distance-dependent function. The quality of the resulting analysis and forecast is greatly influenced by the choice of the localization function parameters, e.g., the radius of influence. The localization radius is generally tuned empirically to yield desirable results.This work, proposes two adaptive algorithms for covariance localization in the EnKF framework, both based on a machine learning approach. The first algorithm adapts the localization radius in time, while the second algorithm tunes the localization radius in both time and space. Numerical experiments carried out with the Lorenz-96 model, and a quasi-geostrophic model, reveal the potential of the proposed machine learning approaches.
]]></description>
<dc:subject>modeling machine-learning prediction rather-interesting looking-to-see approximation algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1b0d4f68558d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<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:approximation"/>
	<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://scholar.google.com/scholar?q=jensen+cohen+multiple+comparisons">
    <title>&quot;Multiple comparisons in induction algorithms&quot; - Google Scholar</title>
    <dc:date>2018-02-27T11:33:53+00:00</dc:date>
    <link>https://scholar.google.com/scholar?q=jensen+cohen+multiple+comparisons</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>machine-learning statistics modeling performance-measure consider:lexicase to-write-about nudge</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d053061a5882/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://christophm.github.io/interpretable-ml-book/">
    <title>Interpretable Machine Learning</title>
    <dc:date>2018-02-27T11:24:17+00:00</dc:date>
    <link>https://christophm.github.io/interpretable-ml-book/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning has a huge potential to improve products, processes and research. But machines usually don’t give an explanation for their predictions, which hurts trust and creates a barrier for the adoption of machine learning. This book is about making machine learning models and their decisions interpretable.

]]></description>
<dc:subject>modeling statistics rather-interesting interpretability explanation to-write-about visualization machine-learning book</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7c2edebeaeee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:book"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1712.00180">
    <title>[1712.00180] New Techniques for Inferring L-Systems Using Genetic Algorithm</title>
    <dc:date>2018-01-15T15:21:58+00:00</dc:date>
    <link>https://arxiv.org/abs/1712.00180</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Lindenmayer systems (L-systems) are a formal grammar system that iteratively rewrites all symbols of a string, in parallel. When visualized with a graphical interpretation, the images have self-similar shapes that appear frequently in nature, and they have been particularly successful as a concise, reusable technique for simulating plants. The L-system inference problem is to find an L-system to simulate a given plant. This is currently done mainly by experts, but this process is limited by the availability of experts, the complexity that may be solved by humans, and time. This paper introduces the Plant Model Inference Tool (PMIT) that infers deterministic context-free L-systems from an initial sequence of strings generated by the system using a genetic algorithm. PMIT is able to infer more complex systems than existing approaches. Indeed, while existing approaches are limited to L-systems with a total sum of 20 combined symbols in the productions, PMIT can infer almost all L-systems tested where the total sum is 140 symbols. This was validated using a test bed of 28 previously developed L-system models, in addition to models created artificially by bootstrapping larger models.
]]></description>
<dc:subject>L-systems Lindenmayer-systems inference rewriting-systems rather-interesting modeling to-write-about consider:more-abstract-versions</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ef534cc88579/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:L-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Lindenmayer-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rewriting-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:more-abstract-versions"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.04380">
    <title>[1709.04380] Neural Network Based Nonlinear Weighted Finite Automata</title>
    <dc:date>2018-01-15T11:38:32+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.04380</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent successes of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinearWFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFAand relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real-world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.
]]></description>
<dc:subject>formal-languages automata rather-interesting neural-networks representation statistics modeling to-write-about consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:41045df28f23/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formal-languages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<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/1704.06960">
    <title>[1704.06960] Translating Neuralese</title>
    <dc:date>2018-01-02T13:26:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.06960</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge. Here we propose to interpret agents' messages by translating them. Unlike in typical machine translation problems, we have no parallel data to learn from. Instead we develop a translation model based on the insight that agent messages and natural language strings mean the same thing if they induce the same belief about the world in a listener. We present theoretical guarantees and empirical evidence that our approach preserves both the semantics and pragmatics of messages by ensuring that players communicating through a translation layer do not suffer a substantial loss in reward relative to players with a common language.
]]></description>
<dc:subject>interpretability modeling rather-interesting neural-networks algorithms basic-science to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0141aaa361db/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:basic-science"/>
	<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/1711.01129">
    <title>[1711.01129] Hamilton-Jacobi Theory and Information Geometry</title>
    <dc:date>2017-12-11T12:40:06+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.01129</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recently, a method to dynamically define a divergence function D for a given statistical manifold (,g,T) by means of the Hamilton-Jacobi theory associated with a suitable Lagrangian function 𝔏 on T has been proposed. Here we will review this construction and lay the basis for an inverse problem where we assume the divergence function D to be known and we look for a Lagrangian function 𝔏 for which D is a complete solution of the associated Hamilton-Jacobi theory. To apply these ideas to quantum systems, we have to replace probability distributions with probability amplitudes.]]></description>
<dc:subject>information-geometry statistics information-theory to-understand modeling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ba67f7c9e0cd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1603.02597">
    <title>[1603.02597] Prediction of Infinite Words with Automata</title>
    <dc:date>2017-11-05T14:35:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1603.02597</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the classic problem of sequence prediction, a predictor receives a sequence of values from an emitter and tries to guess the next value before it appears. The predictor masters the emitter if there is a point after which all of the predictor's guesses are correct. In this paper we consider the case in which the predictor is an automaton and the emitted values are drawn from a finite set; i.e., the emitted sequence is an infinite word. We examine the predictive capabilities of finite automata, pushdown automata, stack automata (a generalization of pushdown automata), and multihead finite automata. We relate our predicting automata to purely periodic words, ultimately periodic words, and multilinear words, describing novel prediction algorithms for mastering these sequences.]]></description>
<dc:subject>formal-languages automata consider:looking-to-see prediction modeling to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8442e47e6ed1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formal-languages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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/1701.07681">
    <title>[1701.07681] Fast and Accurate Time Series Classification with WEASEL</title>
    <dc:date>2017-11-03T11:44:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.07681</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Time series (TS) occur in many scientific and commercial applications, ranging from earth surveillance to industry automation to the smart grids. An important type of TS analysis is classification, which can, for instance, improve energy load forecasting in smart grids by detecting the types of electronic devices based on their energy consumption profiles recorded by automatic sensors. Such sensor-driven applications are very often characterized by (a) very long TS and (b) very large TS datasets needing classification. However, current methods to time series classification (TSC) cannot cope with such data volumes at acceptable accuracy; they are either scalable but offer only inferior classification quality, or they achieve state-of-the-art classification quality but cannot scale to large data volumes. 
In this paper, we present WEASEL (Word ExtrAction for time SEries cLassification), a novel TSC method which is both scalable and accurate. Like other state-of-the-art TSC methods, WEASEL transforms time series into feature vectors, using a sliding-window approach, which are then analyzed through a machine learning classifier. The novelty of WEASEL lies in its specific method for deriving features, resulting in a much smaller yet much more discriminative feature set. On the popular UCR benchmark of 85 TS datasets, WEASEL is more accurate than the best current non-ensemble algorithms at orders-of-magnitude lower classification and training times, and it is almost as accurate as ensemble classifiers, whose computational complexity makes them inapplicable even for mid-size datasets. The outstanding robustness of WEASEL is also confirmed by experiments on two real smart grid datasets, where it out-of-the-box achieves almost the same accuracy as highly tuned, domain-specific methods.
]]></description>
<dc:subject>time-series classification feature-construction rather-interesting modeling to-write-about to-do consider:robustness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:67e1cdce17dc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.00479">
    <title>[1710.00479] Factor selection by permutation</title>
    <dc:date>2017-10-24T11:10:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.00479</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Researchers often have data measuring features xij of samples, such as test scores of students. In factor analysis and PCA, these features are thought to be influenced by unobserved factors, such as skills. Can we determine how many factors affect the data? Many approaches have been developed for this factor selection problem. The popular Parallel Analysis method randomly permutes each feature of the data. It selects factors if their singular values are larger than those of the permuted data. It is used by leading applied statisticians, including T Hastie, M Stephens, J Storey, R Tibshirani and WH Wong. Despite empirical evidence for its accuracy, there is currently no theoretical justification. This prevents us from knowing when it will work in the future. 
In this paper, we show that parallel analysis consistently selects the significant factors in certain high-dimensional factor models. The intuition is that permutations keep the noise invariant, while "destroying" the low-rank signal. This provides justification for permutation methods in PCA and factor models under some conditions. A key requirement is that the factors must load on several variables. Our work points to improvements of permutation methods.]]></description>
<dc:subject>modeling statistics rather-interesting information-theory signal-processing feature-extraction looking-to-see to-write-about consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:517a691e7ffc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1612.08699">
    <title>[1612.08699] Comparative Causal Mediation: Relaxing the Assumption of No Mediator-Outcome Confounding</title>
    <dc:date>2017-10-22T17:10:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1612.08699</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Experiments often include multiple treatments, with the primary goal to compare the causal effects of multiple treatments. While comparing the magnitudes of the average treatment effects (ATEs) is straightforward, there exist few methods to systematically compare the causal anatomies of each treatment (that is, the collection of causal mechanisms underlying each treatment's total effect) in order to understand the sources of their relative magnitudes. This study introduces a framework for comparing the causal anatomies of multiple treatments through the use of causal mediation analysis. The study proposes a set of comparative causal mediation estimands that compare the mediation effects of different treatments via a common mediator. It derives the properties of a set of estimators, which are shown to be consistent (or conservative) without making the assumption of no unobserved confounding of the mediator-outcome relationship, which is a strong and nonrefutable assumption that must be made for consistent estimation of individual causal mediation effects. The estimators are easy to understand and implement, thereby providing researchers with a simple, reliable, and systematic method of comparing, discovering, and testing the causal mechanism differences between multiple treatments. An original application is presented to illustrate the method.]]></description>
<dc:subject>experimental-design statistics rather-interesting modeling out-of-the-box philosophy-of-science algorithms to-write-about to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3ddb57f63162/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:out-of-the-box"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<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-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1602.01241">
    <title>[1602.01241] Using separable non-negative matrix factorization techniques for the analysis of time-resolved Raman spectra</title>
    <dc:date>2017-10-15T11:35:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1602.01241</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The key challenge of time-resolved Raman spectroscopy is the identification of the constituent species and the analysis of the kinetics of the underlying reaction network. In this work we present an integral approach that allows for determining both the component spectra and the rate constants simultaneously from a series of vibrational spectra. It is based on an algorithm for non-negative matrix factorization which is applied to the experimental data set following a few pre-processing steps. As a prerequisite for physically unambiguous solutions, each component spectrum must include one vibrational band that does not significantly interfere with vibrational bands of other species. The approach is applied to synthetic "experimental" spectra derived from model systems comprising a set of species with component spectra differing with respect to their degree of spectral interferences and signal-to-noise ratios. In each case, the species involved are connected via monomolecular reaction pathways. The potential and limitations of the approach for recovering the respective rate constants and component spectra are discussed.
]]></description>
<dc:subject>spectroscopy data-analysis inference numerical-methods modeling statistics rather-interesting nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:250c667d5ab4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:spectroscopy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.08617">
    <title>[1705.08617] Which bridge estimator is optimal for variable selection?</title>
    <dc:date>2017-10-12T11:10:48+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.08617</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study the problem of variable selection for linear models under the high dimensional asymptotic setting, where the number of observations n grows at the same rate as the number of predictors p. We consider two stage variable selection techniques (TVS) in which the first stage uses bridge estimators to obtain an estimate of the regression coefficients, and the second stage simply thresholds the regression coefficients estimate to select the "important" predictors. The asymptotic false discovery proportion (AFDP) and true positive proportion (ATPP) of these TVS are evaluated. We prove that for a fixed ATTP, in order to obtain the smallest AFDP one should pick an estimator that minimizes the asymptotic mean square error in the first stage of TVS. This simple observation enables us to evaluate and compare the performances of different TVS with each other and with some standard variable selection techniques, such as LASSO and Sure Independence Screening. For instance, we prove that a TVS with LASSO in its first stage can outperform LASSO (only one stage) in a large range of ATTP. Furthermore, we will show that for large values of noise, a TVS with ridge in its first stage outperforms TVS with other bridge estimators including the one that has LASSO in its first stage.
]]></description>
<dc:subject>variable-selection modeling algorithms statistics nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8cfba12fc85c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:variable-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://tedunderwood.com/2017/07/13/were-probably-due-for-another-discussion-of-stanley-fish/">
    <title>We’re probably due for another discussion of Stanley Fish | The Stone and the Shell</title>
    <dc:date>2017-10-08T01:49:25+00:00</dc:date>
    <link>https://tedunderwood.com/2017/07/13/were-probably-due-for-another-discussion-of-stanley-fish/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Of course, if you pursue that approach systematically enough, it will lead you away from topic modeling toward methods that rely more explicitly on human judgment. I have been leaning on supervised algorithms a lot lately—not because they’re easier to test or more reliable than unsupervised ones—but because they explicitly acknowledge that interpretation has to be anchored in human history.

At a first glance, this may seem to make progress impossible. “All we can ever discover is which books resemble these other books selected by a particular group of readers. The algorithm can only reproduce a category someone else already defined!” And yes, supervised modeling is circular. But this is a circularity shared by all interpretation of history, and it never merely reproduces its starting point. You can discover that books resemble each other to different degrees. You can discover that models defined by the responses of one interpretive community do or don’t align with models of another. And often you can, carefully, provisionally, draw explanatory inferences from the model itself, assisted perhaps by a bit of close reading.

]]></description>
<dc:subject>digital-humanities machine-learning reasonableness it's-more-complicated-than-you-think modeling philosophy criticism to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:df931316753a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reasonableness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:it's-more-complicated-than-you-think"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:criticism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522">
    <title>Tracing co-regulatory network dynamics in noisy, single-cell transcriptome trajectories | bioRxiv</title>
    <dc:date>2017-10-03T11:01:27+00:00</dc:date>
    <link>https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The availability of gene expression data at the single cell level makes it possible to probe the molecular underpinnings of complex biological processes such as differentiation and oncogenesis. Promising new methods have emerged for reconstructing a progression 'trajectory' from static single-cell transcriptome measurements. However, it remains unclear how to adequately model the appreciable level of noise in these data to elucidate gene regulatory network rewiring. Here, we present a framework called Single Cell Inference of MorphIng Trajectoiries and their Associated Regulation (SCIMITAR) that infers progressions from static single-cell transcriptomes by employing a continuous parametrization of Gaussian mixtures in high-dimensional curves. SCIMITAR yields rich models from the data that highlight genes with expression and coexpression patterns that are associated with the inferred progression. Further, SCIMITAR extracts regulatory states from the implicated trajectory-evolving co-expression networks. We benchmark the method on simulated data to show that it yields accurate cell ordering and gene network inferences. Applied to the interpretation of a single-cell human fetal neuron dataset, SCIMITAR finds progression-associated genes in cornerstone neural differentiation pathways missed by standard differential expression tests. Finally, by leveraging the rewiring of gene-gene co-expression relations across the progression, the method reveals the rise and fall of co-regulatory states and trajectory-dependent gene modules. These analyses implicate new transcription factors in neural differentiation including putative co-factors for the multi-functional NFAT pathway.

]]></description>
<dc:subject>gene-regulatory-networks bioinformatics systems-biology rather-interesting modeling experiment nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2f149bc59c46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<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/1701.08085">
    <title>[1701.08085] The Biological Consequences of the Computational World: Mathematical Reflections on Cancer Biology</title>
    <dc:date>2017-09-26T11:54:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.08085</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The role of continua has been clear since antiquity in the mathematical approaches to physics, while discrete manifolds were brought to the limelight mostly by Quantum and Information Theories, in the XX century. We first recall how theorizing and measuring radically change in physics when using discrete vs. continuous mathematical manifolds. It will follow that the reference to discrete structures and digital information is far from neutral in knowledge construction. In biology, in particular, the introduction of information as a new observable on discrete data types has been promoting a dramatic reorganization of the tools for knowledge. We briefly analyze the origin and the nature, then some consequences of the bias thus induced in life sciences, with particular emphasis on research on cancer. We finally summarize new theoretical frames that propose different directions as for the organizing principles for biological thinking and experimenting, including in cancer research. Cancer is now viewed as an organismal, tissue based issue, according to the perspective proposed in (Sonnenschein, Soto, 1999; Baker, 2015).]]></description>
<dc:subject>representation philosophy-of-science theoretical-biology bioinformatics systems-biology modeling to-write-about define-your-terms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:591b903d92f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1011.4245">
    <title>[1011.4245] When the optimal is not the best: parameter estimation in complex biological models</title>
    <dc:date>2017-05-09T16:21:43+00:00</dc:date>
    <link>https://arxiv.org/abs/1011.4245</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Background: The vast computational resources that became available during the past decade enabled the development and simulation of increasingly complex mathematical models of cancer growth. These models typically involve many free parameters whose determination is a substantial obstacle to model development. Direct measurement of biochemical parameters in vivo is often difficult and sometimes impracticable, while fitting them under data-poor conditions may result in biologically implausible values. 
Results: We discuss different methodological approaches to estimate parameters in complex biological models. We make use of the high computational power of the Blue Gene technology to perform an extensive study of the parameter space in a model of avascular tumor growth. We explicitly show that the landscape of the cost function used to optimize the model to the data has a very rugged surface in parameter space. This cost function has many local minima with unrealistic solutions, including the global minimum corresponding to the best fit. 
Conclusions: The case studied in this paper shows one example in which model parameters that optimally fit the data are not necessarily the best ones from a biological point of view. To avoid force-fitting a model to a dataset, we propose that the best model parameters should be found by choosing, among suboptimal parameters, those that match criteria other than the ones used to fit the model. We also conclude that the model, data and optimization approach form a new complex system, and point to the need of a theory that addresses this problem more generally.
]]></description>
<dc:subject>optimization biophysics noise stochastic-resonance modeling rather-interesting to-write-about approximation performance-measure</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9e3152d08faa/</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:biophysics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:noise"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stochastic-resonance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1609.08312">
    <title>[1609.08312] Duality between Feature Selection and Data Clustering</title>
    <dc:date>2017-05-09T11:07:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1609.08312</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The feature-selection problem is formulated from an information-theoretic perspective. We show that the problem can be efficiently solved by an extension of the recently proposed info-clustering paradigm. This reveals the fundamental duality between feature selection and data clustering,which is a consequence of the more general duality between the principal partition and the principal lattice of partitions in combinatorial optimization.
]]></description>
<dc:subject>information-theory modeling define-your-terms feature-extraction to-understand connections-made statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:77e85d4304a8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:connections-made"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1501.01300">
    <title>[1501.01300] Minimum Probabilistic Finite State Learning Problem on Finite Data Sets: Complexity, Solution and Approximations</title>
    <dc:date>2017-03-24T13:24:40+00:00</dc:date>
    <link>https://arxiv.org/abs/1501.01300</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we study the problem of determining a minimum state probabilistic finite state machine capable of generating statistically identical symbol sequences to samples provided. This problem is qualitatively similar to the classical Hidden Markov Model problem and has been studied from a practical point of view in several works beginning with the work presented in: Shalizi, C.R., Shalizi, K.L., Crutchfield, J.P. (2002) \textit{An algorithm for pattern discovery in time series.} Technical Report 02-10-060, Santa Fe Institute. arxiv.org/abs/cs.LG/0210025. We show that the underlying problem is NP-hard and thus all existing polynomial time algorithms must be approximations on finite data sets. Using our NP-hardness proof, we show how to construct a provably correct algorithm for constructing a minimum state probabilistic finite state machine given data and empirically study its running time.
]]></description>
<dc:subject>hey-I-know-this-guy automata time-series optimization modeling performance-measure computational-complexity rather-interesting to-write-about nudge-targets consider:rewriting-the-damned-algorithm</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b0341b6fad5b/</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:automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<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: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:rewriting-the-damned-algorithm"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2017/03/04/113720?rss=1">
    <title>The Past Sure Is Tense: On Interpreting Phylogenetic Divergence Time Estimates | bioRxiv</title>
    <dc:date>2017-03-24T11:29:31+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2017/03/04/113720?rss=1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Divergence time estimation --- the calibration of a phylogeny to geological time --- is a integral first step in modelling the tempo of biological evolution (traits and lineages). However, despite increasingly sophisticated methods to infer divergence times from molecular genetic sequences, the estimated age of many nodes across the tree of life contrast significantly and consistently with timeframes conveyed by the fossil record. This is perhaps best exemplified by crown angiosperms, where molecular clock (Triassic) estimates predate the oldest (Early Cretaceous) undisputed angiosperm fossils by tens of millions of years or more. While the incompleteness of the fossil record is a common concern, issues of data limitation and model inadequacy are viable (if underexplored) alternative explanations. In this vein, Beaulieu et al. (2015) convincingly demonstrated how methods of divergence time inference can be misled by both (i) extreme state-dependent molecular substitution rate heterogeneity and (ii) biased sampling of representative major lineages. While these (essentially model-violation) results are robust (and probably common in empirical data sets), we note a further alternative: that the configuration of the statistical inference problem alone precluded the reconstruction of the paleontological timeframe for the crown age of angiosperms. We demonstrate, through sampling from the joint prior (formed by combining the tree (diversification) prior with the various calibration densities specified for fossil-calibrated nodes), that with no data present at all, an Early Cretaceous crown angiosperms is rejected (i.e., has essentially zero probability). More worrisome, however, is that for the 24 nodes calibrated by fossils, almost all have indistinguishable marginal prior and posterior age distributions, indicating an absence of relevant information in the data. Given that these calibrated nodes are strategically placed in disparate regions of the tree, they essentially anchor the tree scaffold, and so the posterior inference for the tree as a whole is largely determined by the pseudo-data present in the (often arbitrary) calibration densities. We recommend, as for any Bayesian analysis, that marginal prior and posterior distributions be carefully compared, especially for parameters of direct interest. Finally, we note that the results presented here do not refute the biological modelling concerns identified by Beaulieu et al. (2015). Both sets of issues remain apposite to the goals of accurate divergence time estimation, and only by considering them in tandem can we move forward more confidently.

]]></description>
<dc:subject>cladistics statistics modeling paleontology inference rather-interesting modeling-is-not-mathematics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:58f867a7c3d8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cladistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:paleontology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.05571">
    <title>[1611.05571] Random matrix approach to estimation of high-dimensional factor models</title>
    <dc:date>2017-03-21T22:36:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.05571</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In dealing with high-dimensional data sets, factor models are often useful for dimension reduction. The estimation of factor models has been actively studied in various fields. In the first part of this paper, we present a new approach to estimate high-dimensional factor models, using the empirical spectral density of residuals. The spectrum of covariance matrices from financial data typically exhibits two characteristic aspects: a few spikes and bulk. The former represent factors that mainly drive the features and the latter arises from idiosyncratic noise. Motivated by these two aspects, we consider a minimum distance between two spectrums; one from a covariance structure model and the other from real residuals of financial data that are obtained by subtracting principal components. Our method simultaneously provides estimators of the number of factors and information about correlation structures in residuals. Using free random variable techniques, the proposed algorithm can be implemented and controlled effectively. Monte Carlo simulations confirm that our method is robust to noise or the presence of weak factors. Furthermore, the application to financial time-series shows that our estimators capture essential aspects of market dynamics.
]]></description>
<dc:subject>time-series probability-theory modeling dimension-reduction random-matrices to-understand statistics algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a7fd4c12e294/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:random-matrices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1605.06336">
    <title>[1605.06336] Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA</title>
    <dc:date>2017-03-11T13:08:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.06336</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Nonlinear independent component analysis (ICA) provides an appealing framework for unsupervised feature learning, but the models proposed so far are not identifiable. Here, we first propose a new intuitive principle of unsupervised deep learning from time series which uses the nonstationary structure of the data. Our learning principle, time-contrastive learning (TCL), finds a representation which allows optimal discrimination of time segments (windows). Surprisingly, we show how TCL can be related to a nonlinear ICA model, when ICA is redefined to include temporal nonstationarities. In particular, we show that TCL combined with linear ICA estimates the nonlinear ICA model up to point-wise transformations of the sources, and this solution is unique --- thus providing the first identifiability result for nonlinear ICA which is rigorous, constructive, as well as very general.
]]></description>
<dc:subject>time-series modeling algorithms machine-learning unsupervised-learning pattern-discovery feature-extraction to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c3f0935f76e9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.07306">
    <title>[1702.07306] Causal Discovery Using Proxy Variables</title>
    <dc:date>2017-03-05T22:44:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.07306</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Discovering causal relations is fundamental to reasoning and intelligence. In particular, observational causal discovery algorithms estimate the cause-effect relation between two random entities X and Y, given n samples from P(X,Y). 
In this paper, we develop a framework to estimate the cause-effect relation between two static entities x and y: for instance, an art masterpiece x and its fraudulent copy y. To this end, we introduce the notion of proxy variables, which allow the construction of a pair of random entities (A,B) from the pair of static entities (x,y). Then, estimating the cause-effect relation between A and B using an observational causal discovery algorithm leads to an estimation of the cause-effect relation between x and y. For example, our framework detects the causal relation between unprocessed photographs and their modifications, and orders in time a set of shuffled frames from a video. 
As our main case study, we introduce a human-elicited dataset of 10,000 pairs of casually-linked pairs of words from natural language. Our methods discover 75% of these causal relations. Finally, we discuss the role of proxy variables in machine learning, as a general tool to incorporate static knowledge into prediction tasks.
]]></description>
<dc:subject>modeling cause-and-effect inference learning-by-watching rather-interesting to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:608da0343b9e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cause-and-effect"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1105.6344#">
    <title>[1105.6344] Prototype selection for parameter estimation in complex models</title>
    <dc:date>2017-02-27T12:34:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1105.6344#</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Parameter estimation in astrophysics often requires the use of complex physical models. In this paper we study the problem of estimating the parameters that describe star formation history (SFH) in galaxies. Here, high-dimensional spectral data from galaxies are appropriately modeled as linear combinations of physical components, called simple stellar populations (SSPs), plus some nonlinear distortions. Theoretical data for each SSP is produced for a fixed parameter vector via computer modeling. Though the parameters that define each SSP are continuous, optimizing the signal model over a large set of SSPs on a fine parameter grid is computationally infeasible and inefficient. The goal of this study is to estimate the set of parameters that describes the SFH of each galaxy. These target parameters, such as the average ages and chemical compositions of the galaxy's stellar populations, are derived from the SSP parameters and the component weights in the signal model. Here, we introduce a principled approach of choosing a small basis of SSP prototypes for SFH parameter estimation. The basic idea is to quantize the vector space and effective support of the model components. In addition to greater computational efficiency, we achieve better estimates of the SFH target parameters. In simulations, our proposed quantization method obtains a substantial improvement in estimating the target parameters over the common method of employing a parameter grid. Sparse coding techniques are not appropriate for this problem without proper constraints, while constrained sparse coding methods perform poorly for parameter estimation because their objective is signal reconstruction, not estimation of the target parameters.
]]></description>
<dc:subject>astronomy archetypal-analysis dimension-reduction big-data modeling to-write-about performance-measure rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:84d0de6ee555/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:astronomy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:big-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/astro-ph/0301491">
    <title>[astro-ph/0301491] Archetypal analysis of galaxy spectra</title>
    <dc:date>2017-02-27T01:25:19+00:00</dc:date>
    <link>https://arxiv.org/abs/astro-ph/0301491</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Archetypal analysis represents each individual member of a set of data vectors as a mixture (a constrained linear combination) of the pure types or archetypes of the data set. The archetypes are themselves required to be mixtures of the data vectors. Archetypal analysis may be particularly useful in analysing data sets comprising galaxy spectra, since each spectrum is, presumably, a superposition of the emission from the various stellar populations, nebular emissions and nuclear activity making up that galaxy, and each of these emission sources corresponds to a potential archetype of the entire data set. We demonstrate archetypal analysis using sets of composite synthetic galaxy spectra, showing that the method promises to be an effective and efficient way to classify spectra. We show that archetypal analysis is robust in the presence of various types of noise.
]]></description>
<dc:subject>archetypal-analysis modeling dimension-reduction rather-interesting to-write-about to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4e51670b4d3d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<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-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.01331">
    <title>[1611.01331] RenderGAN: Generating Realistic Labeled Data</title>
    <dc:date>2017-02-25T13:33:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.01331</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g. lighting, background, and detail) are learned from unlabeled data such that the generated images are strikingly realistic while preserving the labels known from the 3D model. We apply the RenderGAN framework to generate images of barcode-like markers that are attached to honeybees. Training a DCNN on data generated by the RenderGAN yields considerably better performance than training it on various baselines.
]]></description>
<dc:subject>generative-models rather-interesting synthetic-data interpolation modeling algorithms deep-learning nudge-targets consider:looking-to-see to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:97501ea54b10/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:synthetic-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpolation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<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/1701.07667">
    <title>[1701.07667] Indistinguishable sceneries on the Boolean hypercube</title>
    <dc:date>2017-02-25T13:25:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.07667</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We show that the scenery reconstruction problem on the Boolean hypercube is in general impossible. This is done by using locally biased functions, in which every vertex has a constant fraction of neighbors colored by 1, and locally stable functions, in which every vertex has a constant fraction of neighbors colored by its own color. Our methods are constructive, and also give super-polynomial lower bounds on the number of locally biased and locally stable functions. We further show similar results for ℤn and other graphs, and offer several follow-up questions.]]></description>
<dc:subject>combinatorics modeling learning-by-watching rather-interesting open-questions consider:generalizing consider:looking-to-see to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:527f7d62624c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-questions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:generalizing"/>
	<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/1702.04917">
    <title>[1702.04917] Compressed sensing in Hilbert spaces</title>
    <dc:date>2017-02-25T13:05:02+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.04917</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In many linear inverse problems, we want to estimate an unknown vector belonging to a high-dimensional (or infinite-dimensional) space from few linear measurements. To overcome the ill-posed nature of such problems, we use a low-dimension assumption on the unknown vector: it belongs to a low-dimensional model set. The question of whether it is possible to recover such an unknown vector from few measurements then arises. If the answer is yes, it is also important to be able to describe a way to perform such a recovery. We describe a general framework where appropriately chosen random measurements guarantee that recovery is possible. We further describe a way to study the performance of recovery methods that consist in the minimization of a regularization function under a data-fit constraint.
]]></description>
<dc:subject>approximation compressed-sensing inference modeling algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6c6cf56ba470/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1701.03230">
    <title>[1701.03230] Surface Reconstruction with Data-driven Exemplar Priors</title>
    <dc:date>2017-02-25T12:27:30+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.03230</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we propose a framework to reconstruct 3D models from raw scanned points by learning the prior knowledge of a specific class of objects. Unlike previous work that heuristically specifies particular regularities and defines parametric models, our shape priors are learned directly from existing 3D models under a framework based on affinity propagation. Given a database of 3D models within the same class of objects, we build a comprehensive library of 3D local shape priors. We then formulate the problem to select as-few-as-possible priors from the library, referred to as exemplar priors. These priors are sufficient to represent the 3D shapes of the whole class of objects from where they are generated. By manipulating these priors, we are able to reconstruct geometrically faithful models with the same class of objects from raw point clouds. Our framework can be easily generalized to reconstruct various categories of 3D objects that have more geometrically or topologically complex structures. Comprehensive experiments exhibit the power of our exemplar priors for gracefully solving several problems in 3D shape reconstruction such as preserving sharp features, recovering fine details and so on.
]]></description>
<dc:subject>computational-geometry inference statistics algorithms rather-interesting approximation modeling nudge-targets consider:performance-measures consider:parsimony</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e2a0732b69d0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<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:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:parsimony"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.02707">
    <title>[1702.02707] A Fast Algorithm for the Coordinate-wise Minimum Distance Estimation</title>
    <dc:date>2017-02-23T22:20:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.02707</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Application of the minimum distance method to the linear regression model for estimating regression parameters is a difficult and time-consuming process due to the complexity of its distance function, and hence, it is computationally expensive. To deal with the computational cost, this paper proposes a fast algorithm which mainly uses technique of coordinate-wise minimization in order to estimate the regression parameters. R package based on the proposed algorithm and written in Rcpp is available online.
]]></description>
<dc:subject>statistics modeling goodness-of-fit numerical-methods algorithms to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2f40fb479e2d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:goodness-of-fit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1605.06096">
    <title>[1605.06096] Consensus+Innovations Distributed Kalman Filter with Optimized Gains</title>
    <dc:date>2017-02-23T22:17:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.06096</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we address the distributed filtering and prediction of time-varying random fields represented by linear time-invariant (LTI) dynamical systems. The field is observed by a sparsely connected network of agents/sensors collaborating among themselves. We develop a Kalman filter type consensus+innovations distributed linear estimator of the dynamic field termed as Consensus+Innovations Kalman Filter. We analyze the convergence properties of this distributed estimator. We prove that the mean-squared error of the estimator asymptotically converges if the degree of instability of the field dynamics is within a pre-specified threshold defined as tracking capacity of the estimator. The tracking capacity is a function of the local observation models and the agent communication network. We design the optimal consensus and innovation gain matrices yielding distributed estimates with minimized mean-squared error. Through numerical evaluations, we show that, the distributed estimator with optimal gains converges faster and with approximately 3dB better mean-squared error performance than previous distributed estimators.
]]></description>
<dc:subject>to-understand modeling statistics no-really-I-don't-understand representation ??</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fbe828c9f00c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:no-really-I-don't-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:??"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1701.03757">
    <title>[1701.03757] Deep Probabilistic Programming</title>
    <dc:date>2017-01-24T12:22:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.03757</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose Edward, a Turing-complete probabilistic programming language. Edward builds on two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. For flexibility, Edward makes it easy to fit the same model using a variety of composable inference methods, ranging from point estimation, to variational inference, to MCMC. In addition, Edward can reuse the modeling representation as part of inference, facilitating the design of rich variational models and generative adversarial networks. For efficiency, Edward is integrated into TensorFlow, providing significant speedups over existing probabilistic systems. For example, on a benchmark logistic regression task, Edward is at least 35x faster than Stan and PyMC3.
]]></description>
<dc:subject>probabilistic-programming programming-language rather-interesting modeling representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7e7208091c01/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probabilistic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:programming-language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1610.08910">
    <title>[1610.08910] Perfect Memory Context Trees in time series modeling</title>
    <dc:date>2017-01-12T21:43:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1610.08910</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The Stochastic Context Tree (SCOT) is a useful tool for studying infinite random sequences generated by an m-Markov Chain (m-MC). It captures the phenomenon that the probability distribution of the next state sometimes depends on less than m of the preceding states. This allows compressing the information needed to describe an m-MC. The SCOT construction has been earlier used under various names: VLMC, VOMC, PST, CTW. In this paper we study the possibility of reducing the m-MC to a 1-MC on the leaves of the SCOT. Such context trees are called perfect-memory. We give various combinatorial characterizations of perfect-memory context trees and an efficient algorithm to find the minimal perfect-memory extension of a SCOT.
]]></description>
<dc:subject>data-structures Markov-models stochastic-systems modeling rather-odd to-understand representation time-series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b46cde1a60ae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-structures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Markov-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stochastic-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-odd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1612.01605">
    <title>[1612.01605] Zipf's law, unbounded complexity and open-ended evolution</title>
    <dc:date>2016-12-17T13:44:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1612.01605</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A major problem for evolutionary theory is understanding the so called {\em open-ended} nature of evolutionary change. Open-ended evolution (OEE) refers to the unbounded increase in complexity that seems to characterise evolution on multiple scales. This property seems to be a characteristic feature of biological and technological evolution and is strongly tied to the generative potential associated with combinatorics, which allows the system to grow and expand their available state spaces. Several theoretical and computational approaches have been developed to properly characterise OEE. Interestingly, many complex systems displaying OEE, from language to proteins, share a common statistical property: the presence of Zipf's law. Given and inventory of basic items required to build more complex structures Zipf's law tells us that most of these elements are rare whereas a few of them are extremely common. Using Algorithmic Information Theory, in this paper we provide a fundamental definition for open-endedness, which can be understood as {\em postulates}. Its statistical counterpart, based on standard Shannon Information theory, has the structure of a variational problem which is shown to lead to Zipf's law as the expected consequence of an evolutionary processes displaying OEE. We further explore the problem of information conservation through an OEE process and we conclude that statistical information (standard Shannon information) is not conserved, resulting into the paradoxical situation in which the increase of information content has the effect of erasing itself. We prove that this paradox is solved if we consider non-statistical forms of information. This last result implies that standard information theory may not be a suitable theoretical framework to explore the persistence and increase of the information content in OEE systems.
]]></description>
<dc:subject>information-theory open-ended-evolution artificial-life emergent-design emergence approximation modeling to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:20fe0bad5d29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-ended-evolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:emergent-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:emergence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.researchgate.net/publication/256388072_Modeling_Cognition_How_Fiction_Relates_to_Fact">
    <title>Modeling Cognition : How Fiction Relates to Fact (PDF Download Available)</title>
    <dc:date>2016-12-09T12:39:54+00:00</dc:date>
    <link>https://www.researchgate.net/publication/256388072_Modeling_Cognition_How_Fiction_Relates_to_Fact</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The increasing use of computational modeling and simulation methods offers interesting epistemic and theoretical challenges for the philosophy of science. One of the main questions discussed in the philosophical literature relates to the explanatory role of false, unrealistic and sometimes even fictional models. In this paper we argue that (i) some fictional models can offer explanations known as structural model explanations, and (ii) at least some variants of realism, such as the information semantic account of scientific models, can consistently hold that this subset of fictional models are explanatory
]]></description>
<dc:subject>philosophy-of-science modeling modeling-is-not-mathematics cognition</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e15ab4b606a8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cognition"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.06168">
    <title>[1611.06168] On $p$-values</title>
    <dc:date>2016-12-04T14:38:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.06168</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Models are consistently treated as approximations and all procedures are consistent with this. They do not treat the model as being true. In this context p-values are one measure of approximation, a small p-value indicating a poor approximation. Approximation regions are defined and distinguished from confidence regions.]]></description>
<dc:subject>statistics representation modeling modeling-is-not-mathematics rather-interesting to-write-about nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:022fbf966a25/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<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:nudge-targets"/>
	<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/1605.07312">
    <title>[1605.07312] Representation and design of wavelets using unitary circuits</title>
    <dc:date>2016-12-03T15:48:02+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.07312</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The representation of discrete, compact wavelet transformations (WTs) as circuits of local unitary gates is discussed. We employ a similar formalism as used in the multi-scale representation of quantum many-body wavefunctions using unitary circuits, further cementing the relation established in [Phys. Rev. Lett. 116, 140403 (2016)] between classical and quantum multi-scale methods. An algorithm for constructing the circuit representation of known orthogonal, dyadic, discrete WTs is presented, and the explicit representation for Daubechies wavelets, coiflets, and symlets is provided. Furthermore, we demonstrate the usefulness of the circuit formalism in designing novel WTs, including various classes of symmetric wavelets and multi-wavelets, boundary wavelets and biorthogonal wavelets.
]]></description>
<dc:subject>quantums quantum-computing representation wavelets rather-interesting modeling nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:41711c62e333/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quantums"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quantum-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wavelets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.05923">
    <title>[1611.05923] &quot;Influence Sketching&quot;: Finding Influential Samples In Large-Scale Regressions</title>
    <dc:date>2016-11-21T11:26:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.05923</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[There is an especially strong need in modern large-scale data analysis to prioritize samples for manual inspection. For example, the inspection could target important mislabeled samples or key vulnerabilities exploitable by an adversarial attack. In order to solve the "needle in the haystack" problem of which samples to inspect, we develop a new scalable version of Cook's distance, a classical statistical technique for identifying samples which unusually strongly impact the fit of a regression model (and its downstream predictions). In order to scale this technique up to very large and high-dimensional datasets, we introduce a new algorithm which we call "influence sketching." Influence sketching embeds random projections within the influence computation; in particular, the influence score is calculated using the randomly projected pseudo-dataset from the post-convergence General Linear Model (GLM). We validate that influence sketching can reliably and successfully discover influential samples by applying the technique to a malware detection dataset of over 2 million executable files, each represented with almost 100,000 features. For example, we find that randomly deleting approximately 10% of training samples reduces predictive accuracy only slightly from 99.47% to 99.45%, whereas deleting the same number of samples with high influence sketch scores reduces predictive accuracy all the way down to 90.24%. Moreover, we find that influential samples are especially likely to be mislabeled. In the case study, we manually inspect the most influential samples, and find that influence sketching pointed us to new, previously unidentified pieces of malware.
]]></description>
<dc:subject>data-balancing modeling statistics system-of-professions reinvented-again to-write-about nudge-targets consider:looking-to-see consider:feature-discovery consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f6335631dafc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-balancing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reinvented-again"/>
	<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:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.07705">
    <title>[1607.07705] Delineating Parameter Unidentifiabilities in Complex Models</title>
    <dc:date>2016-11-05T11:42:31+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.07705</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Scientists use mathematical modelling to understand and predict the properties of complex physical systems. In highly parameterised models there often exist relationships between parameters over which model predictions are identical, or nearly so. These are known as structural or practical unidentifiabilities, respectively. They are hard to diagnose and make reliable parameter estimation from data impossible. They furthermore imply the existence of an underlying model simplification. We describe a scalable method for detecting unidentifiabilities, and the functional relations defining them, for generic models. This allows for model simplification, and appreciation of which parameters (or functions thereof) cannot be estimated from data. Our algorithm can identify features such as redundant mechanisms and fast timescale subsystems, as well as the regimes in which such approximations are valid. We base our algorithm on a novel quantification of regional parametric sensitivity: multiscale sloppiness. Traditionally, the link between parametric sensitivity and the conditioning of the parameter estimation problem is made locally, through the Fisher Information Matrix. This is valid in the regime of infinitesimal measurement uncertainty. We demonstrate the duality between multiscale sloppiness and the geometry of confidence regions surrounding parameter estimates made where measurement uncertainty is non-negligible. Further theoretical relationships are provided linking multiscale sloppiness to the Likelihood-ratio test. From this, we show that a local sensitivity analysis (as typically done) is insufficient for determining the reliability of parameter estimation, even with simple (non)linear systems. Our algorithm provides a tractable alternative. We finally apply our methods to a large-scale, benchmark Systems Biology model of NF-κB, uncovering previously unknown unidentifiabilities.
]]></description>
<dc:subject>statistics modeling sloppiness philosophy-of-science rather-interesting to-understand performance-measure meta-modeling to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9f32616e0de3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sloppiness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<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:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meta-modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1606.07207">
    <title>[1606.07207] A Boyer-Moore Type Algorithm for Timed Pattern Matching</title>
    <dc:date>2016-07-01T21:46:22+00:00</dc:date>
    <link>http://arxiv.org/abs/1606.07207</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The timed pattern matching problem is formulated by Ulus et al. and has been actively studied since, with its evident application in monitoring real-time systems. The problem takes as input a timed word/signal and a timed pattern (specified either by a timed regular expression or by a timed automaton); and it returns the set of those intervals for which the given timed word, when restricted to the interval, matches the given pattern. We contribute a Boyer-Moore type optimization in timed pattern matching, relying on the classic Boyer-Moore string matching algorithm and its extension to (untimed) pattern matching by Watson and Watson. We assess its effect through experiments; for some problem instances our Boyer-Moore type optimization achieves speed-up by two times, indicating its potential in real-world monitoring tasks where data sets tend to be massive.
]]></description>
<dc:subject>time-series modeling automata classification statistics algorithms representation nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:01ba10345364/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/26/055624">
    <title>Could a neuroscientist understand a microprocessor? | bioRxiv</title>
    <dc:date>2016-05-28T21:04:34+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/26/055624</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[There is a popular belief in neuroscience that we are primarily data limited, that producing large, multimodal, and complex datasets will, enabled by data analysis algorithms, lead to fundamental insights into the way the brain processes information. Microprocessors are among those artificial information processing systems that are both complex and that we understand at all levels, from the overall logical flow, via logical gates, to the dynamics of transistors. Here we take a simulated classical microprocessor as a model organism, and use our ability to perform arbitrary experiments on it to see if popular data analysis methods from neuroscience can elucidate the way it processes information. We show that the approaches reveal interesting structure in the data but do not meaningfully describe the hierarchy of information processing in the processor. This suggests that current approaches in neuroscience may fall short of producing meaningful models of the brain.

]]></description>
<dc:subject>via:numerous neural-networks inference modeling experiment rather-interesting big-data bioinformatics looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cd7d452bf53f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:numerous"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:big-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1604.02008">
    <title>[1604.02008] Stability and Control of Piecewise-Deterministic Queueing Systems</title>
    <dc:date>2016-05-28T11:58:56+00:00</dc:date>
    <link>http://arxiv.org/abs/1604.02008</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Unreliable link capacities cause a significant amount of delay in transportation networks. In this paper, we propose a novel approach to studying the traffic queues due to capacity-reducing events under a class of control policies. First, we propose a Piecewise-Deterministic Queueing (PDQ) model in which the link saturation rates switch between a finite set of values (modes) according to a Markov chain, which captures the occurrence and clearance of capacity-reducing events. Second, we derive results on the stability of PDQ networks, i.e. when the joint distribution of the link queue sizes converges to a unique invariant probability measure. On one hand, a necessary condition for stability is that the average inflow to each link is less than the link's effective capacity. On the other hand, a sufficient condition is that a set of bilinear matrix inequalities involving model parameters and the control policy has a feasible solution. Third, we provide an analytical characterization of the steady-state distribution of bimodal PDQ systems, which enables us to obtain the optimal static/mode-dependent routing policy for bimodal PDQ networks by solving a convex min-cost problem.
]]></description>
<dc:subject>network-theory queueing-theory optimization modeling rather-interesting robustness nudge-targets consider:representation planning consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b259cea6b780/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:queueing-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<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:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.02765">
    <title>[1605.02765] Synthesizing Probabilistic Invariants via Doob's Decomposition</title>
    <dc:date>2016-05-14T13:30:03+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.02765</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[When analyzing probabilistic computations, a powerful approach is to first find a martingale---an expression on the program variables whose expectation remains invariant---and then apply the optional stopping theorem in order to infer properties at termination time. One of the main challenges, then, is to systematically find martingales. 
We propose a novel procedure to synthesize martingale expressions from an arbitrary initial expression. Contrary to state-of-the-art approaches, we do not rely on constraint solving. Instead, we use a symbolic construction based on Doob's decomposition. This procedure can produce very complex martingales, expressed in terms of conditional expectations. 
We show how to automatically generate and simplify these martingales, as well as how to apply the optional stopping theorem to infer properties at termination time. This last step typically involves some simplification steps, and is usually done manually in current approaches. We implement our techniques in a prototype tool and demonstrate our process on several classical examples. Some of them go beyond the capability of current semi-automatic approaches.
]]></description>
<dc:subject>probability-theory probabilistic-programming modeling statistics numerical-methods rather-interesting nudge-targets consider:genetic-programming consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:88dff3fffc57/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probabilistic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.01441">
    <title>[1605.01441] The Dorsal Striatum and the Dynamics of the Consensus Connectomes in the Frontal Lobe of the Human Brain</title>
    <dc:date>2016-05-11T11:40:50+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.01441</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the applications of the graph theory it is unusual that one considers numerous, pairwise different graphs on the very same set of vertices. In the case of human braingraphs or connectomes, however, this is the standard situation: the nodes correspond to anatomically identified cerebral regions, and two vertices are connected by an edge if a diffusion MRI-based workflow identifies a fiber of axons, running between the two regions, corresponding to the two vertices. Therefore, if we examine the braingraphs of n subjects, then we have n graphs on the very same, anatomically identified vertex set. It is a natural idea to describe the k-frequently appearing edges in these graphs: the edges that are present between the same two vertices in at least k out of the n graphs. Based on the NIH-funded large Human Connectome Project's public data release, we have reported the construction of the Budapest Reference Connectome Server \url{this http URL} that generates and visualizes these k-frequently appearing edges. We call the graphs of the k-frequently appearing edges "k-consensus connectomes" since an edge could be included only if it is present in at least k graphs out of n. Considering the whole human brain, we have reported a surprising property of these consensus connectomes earlier. In the present work we are focusing on the frontal lobe of the brain, and we report here a similarly surprising dynamical property of the consensus connectomes when k is gradually changed from k=n to k=1: the connections between the nodes of the frontal lobe are seemingly emanating from those nodes that were connected to sub-cortical structures of the dorsal striatum: the caudate nucleus, and the putamen. We hypothesize that this dynamic behavior copies the axonal fiber development of the frontal lobe.
]]></description>
<dc:subject>neurology connectome graph-theory dynamical-systems rather-interesting inference modeling simulation nudge-targets consider:looking-to-see consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:11387ba65cb3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neurology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:connectome"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.1132">
    <title>[1411.1132] Are you going to the party: depends, who else is coming? [Learning hidden group dynamics via conditional latent tree models]</title>
    <dc:date>2016-03-28T23:03:21+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.1132</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Scalable probabilistic modeling and prediction in high dimensional multivariate time-series is a challenging problem, particularly for systems with hidden sources of dependence and/or homogeneity. Examples of such problems include dynamic social networks with co-evolving nodes and edges and dynamic student learning in online courses. Here, we address these problems through the discovery of hierarchical latent groups. We introduce a family of Conditional Latent Tree Models (CLTM), in which tree-structured latent variables incorporate the unknown groups. The latent tree itself is conditioned on observed covariates such as seasonality, historical activity, and node attributes. We propose a statistically efficient framework for learning both the hierarchical tree structure and the parameters of the CLTM. We demonstrate competitive performance in multiple real world datasets from different domains. These include a dataset on students' attempts at answering questions in a psychology MOOC, Twitter users participating in an emergency management discussion and interacting with one another, and windsurfers interacting on a beach in Southern California. In addition, our modeling framework provides valuable and interpretable information about the hidden group structures and their effect on the evolution of the time series.
]]></description>
<dc:subject>social-networks inference modeling rather-interesting nudge-targets feature-construction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9bcc3b934122/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>