<?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/2512.06522v2"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2603.10941"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2303.13253"/>
	<rdf:li rdf:resource="https://www.pnas.org/doi/10.1073/pnas.2302491120"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.18014"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2409.05746"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=5qNKolRwOkQ"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2006.00840"/>
	<rdf:li rdf:resource="https://link.springer.com/book/10.1007/978-3-642-03942-3"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2405.17919"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2205.14430"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.04574"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.02365"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2010.05170"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.06498"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.02842"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.10168"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.04103"/>
	<rdf:li rdf:resource="https://www.tidyverse.org/learn/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.04157"/>
	<rdf:li rdf:resource="https://www.tidyverse.org/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2010.15662"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2005.00497"/>
	<rdf:li rdf:resource="https://openintro-ims.netlify.app/index.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2103.10357"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.09588"/>
	<rdf:li rdf:resource="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3250568/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.11870"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/10.1101/2021.02.16.431544v1"/>
	<rdf:li rdf:resource="https://picturethismaths.wordpress.com/2021/02/03/three-correlations-and-other-statistical-models/"/>
	<rdf:li rdf:resource="https://pair-code.github.io/lit/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.07801"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1902.07672"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.03634"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/10.1101/2020.05.26.116848v1"/>
	<rdf:li rdf:resource="https://www.knowablemagazine.org/article/health-disease/2020/single-subject-design"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.06853"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.06485"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1511.05219"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/10.1101/393835v1"/>
	<rdf:li rdf:resource="https://www.johndcook.com/blog/2018/05/11/two-sample-t-test/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.05163"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1203.3353"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1601.00670"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1905.13195"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.01248"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.02987"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.10140"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1612.02487"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1405.0825"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1902.00415"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.10140#"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.05740"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.09139"/>
	<rdf:li rdf:resource="https://publications.mfo.de/handle/mfo/1410"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1202.2395"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1410.5115"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1506.08415"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.07481"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.06038"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1707.05033"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.01624"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1712.07381"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.02998"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.07662"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/d41586-019-00857-9"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.06912"/>
	<rdf:li rdf:resource="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0188299"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1101.0891"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.06588"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/2512.06522v2">
    <title>[2512.06522v2] Hierarchical Clustering With Confidence</title>
    <dc:date>2026-05-23T12:01:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2512.06522v2</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Agglomerative hierarchical clustering is one of the most widely used approaches for exploring how observations in a dataset relate to each other. However, its greedy nature makes it highly sensitive to small perturbations in the data, often producing different clustering results and making it difficult to separate genuine structure from spurious patterns. In this paper, we show how randomizing hierarchical clustering can be useful not just for measuring stability but also for designing valid hypothesis testing procedures based on the clustering results.
We propose a simple randomization scheme together with a method for constructing a valid p-value at each node of the hierarchical clustering dendrogram that quantifies evidence against performing the greedy merge. Our test controls the Type I error rate, works with any hierarchical linkage without case-specific derivations, and simulations show it is substantially more powerful than existing selective inference approaches. To demonstrate the practical utility of our p-values, we develop an adaptive α-spending procedure that estimates the number of clusters, with a probabilistic guarantee on overestimation. Experiments on simulated and real data show that this estimate yields powerful clustering and can be used, for example, to assess clustering stability across multiple runs of the randomized algorithm.
]]></description>
<dc:subject>clustering statistics numerical-methods probability-theory unsupervised-learning algorithms rather-interesting to-write-about to-cite consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a39717e23952/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<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:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-cite"/>
	<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/2603.10941">
    <title>[2603.10941] Covariate-adjusted statistical dependence representation through partial copulas: bounds and new insights</title>
    <dc:date>2026-05-22T11:17:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2603.10941</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we revisit the notion of partial copula, originally introduced to test conditional independence, highlighting its capability to represent the dependence between two random variables after removing their dependence with a covariate. Building upon results previously presented in the literature, we show that partial copulas can be seen as a nonlinear analogue of partial correlation. Then, we prove several results showing how dependence properties of the conditional copulas constrain the form of the partial copula. Finally, a simulation study is conducted to illustrate the results and to show the potential of partial copula as a way to describe covariate-adjusted statistical dependence. This highlights the potential of the method to be used in causal inference problems and recover the true sign of a causal effect.
]]></description>
<dc:subject>statistics correlation models models-and-modes to-understand representation causality via:?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:36c7daa074e0/</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:correlation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2303.13253">
    <title>[2303.13253] What is a degree of freedom? Configuration spaces and their topology</title>
    <dc:date>2024-09-28T15:37:42+00:00</dc:date>
    <link>https://arxiv.org/abs/2303.13253</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding degrees of freedom in classical mechanics is fundamental to characterizing physical systems. Counting them is usually easy, especially if we can assign them a clear meaning. However, the precise definition of a degree of freedom is not usually presented in first-year physics courses since it requires mathematical knowledge only learned in more advanced courses. In this paper, we use a pedagogical approach motivated by simple but non-trivial mechanical examples to define degrees of freedom and configuration spaces. We highlight the role that topology plays in understanding these ideas.
]]></description>
<dc:subject>define-your-terms mathematics philosophy-of-science explanation physics statistics to-write-about rather-interesting topology dynamical-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:446c6a5e7624/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:topology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.pnas.org/doi/10.1073/pnas.2302491120">
    <title>An illusion of predictability in scientific results: Even experts confuse inferential uncertainty and outcome variability | PNAS</title>
    <dc:date>2024-09-23T13:21:58+00:00</dc:date>
    <link>https://www.pnas.org/doi/10.1073/pnas.2302491120</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Traditionally, scientists have placed more emphasis on communicating inferential uncertainty (i.e., the precision of statistical estimates) compared to outcome variability (i.e., the predictability of individual outcomes). Here, we show that this can lead to sizable misperceptions about the implications of scientific results. Specifically, we present three preregistered, randomized experiments where participants saw the same scientific findings visualized as showing only inferential uncertainty, only outcome variability, or both and answered questions about the size and importance of findings they were shown. Our results, composed of responses from medical professionals, professional data scientists, and tenure-track faculty, show that the prevalent form of visualizing only inferential uncertainty can lead to significant overestimates of treatment effects, even among highly trained experts. In contrast, we find that depicting both inferential uncertainty and outcome variability leads to more accurate perceptions of results while appearing to leave other subjective impressions of the results unchanged, on average.]]></description>
<dc:subject>science-studies uncertainty define-your-terms theory-and-practice-sitting-in-a-tree rather-interesting statistics folk-science-all-the-way-down social-norms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a8db07b996da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:science-studies"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:uncertainty"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theory-and-practice-sitting-in-a-tree"/>
	<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:folk-science-all-the-way-down"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-norms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.18014">
    <title>[2402.18014] Set-valued Star-Shaped Risk Measures</title>
    <dc:date>2024-09-23T13:18:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.18014</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we introduce a new class of set-valued risk measures, named set-valued star-shaped risk measures. Motivated by the results of scalar monetary and star-shaped risk measures, this paper investigates the representation theorems in the set-valued framework. It is demonstrated that set-valued risk measures can be represented as the union of a family of set-valued convex risk measures, and set-valued normalized star-shaped risk measures can be represented as the union of a family of set-valued normalized convex risk measures. The link between set-valued risk measures and set-valued star-shaped risk measures is also established.
]]></description>
<dc:subject>approximation numerical-methods statistics risk rather-interesting portfolio-theory to-understand geometry error</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2b593313b435/</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:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:risk"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:portfolio-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:error"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2409.05746">
    <title>[2409.05746] LLMs Will Always Hallucinate, and We Need to Live With This</title>
    <dc:date>2024-09-19T15:37:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2409.05746</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[As Large Language Models become more ubiquitous across domains, it becomes important to examine their inherent limitations critically. This work argues that hallucinations in language models are not just occasional errors but an inevitable feature of these systems. We demonstrate that hallucinations stem from the fundamental mathematical and logical structure of LLMs. It is, therefore, impossible to eliminate them through architectural improvements, dataset enhancements, or fact-checking mechanisms. Our analysis draws on computational theory and Godel's First Incompleteness Theorem, which references the undecidability of problems like the Halting, Emptiness, and Acceptance Problems. We demonstrate that every stage of the LLM process-from training data compilation to fact retrieval, intent classification, and text generation-will have a non-zero probability of producing hallucinations. This work introduces the concept of Structural Hallucination as an intrinsic nature of these systems. By establishing the mathematical certainty of hallucinations, we challenge the prevailing notion that they can be fully mitigated.
]]></description>
<dc:subject>machine-learning neural-networks hallucination performance-measure rather-interesting statistics philosophy-of-engineering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ec90a32de8c2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hallucination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=5qNKolRwOkQ">
    <title>Lecture on Maximum Mean Discrepancy (MMD) - YouTube</title>
    <dc:date>2024-08-02T12:33:31+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=5qNKolRwOkQ</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Lecture on MMD statistics for distribution comparisons.]]></description>
<dc:subject>statistics video lecture MMD discrepancy-theory distance metrics rather-interesting to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5adbd28f314d/</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:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:MMD"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrepancy-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<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/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://link.springer.com/book/10.1007/978-3-642-03942-3">
    <title>Geometric Discrepancy: An Illustrated Guide | SpringerLink</title>
    <dc:date>2024-07-16T23:25:09+00:00</dc:date>
    <link>https://link.springer.com/book/10.1007/978-3-642-03942-3</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Discrepancy theory is also called the theory of irregularities of distribution. Here are some typical questions: What is the "most uniform" way of dis­ tributing n points in the unit square? How big is the "irregularity" necessarily present in any such distribution? For a precise formulation of these questions, we must quantify the irregularity of a given distribution, and discrepancy is a numerical parameter of a point set serving this purpose. Such questions were first tackled in the thirties, with a motivation com­ ing from number theory. A more or less satisfactory solution of the basic discrepancy problem in the plane was completed in the late sixties, and the analogous higher-dimensional problem is far from solved even today. In the meantime, discrepancy theory blossomed into a field of remarkable breadth and diversity. There are subfields closely connected to the original number­ theoretic roots of discrepancy theory, areas related to Ramsey theory and to hypergraphs, and also results supporting eminently practical methods and algorithms for numerical integration and similar tasks. The applications in­ clude financial calculations, computer graphics, and computational physics, just to name a few. This book is an introductory textbook on discrepancy theory. It should be accessible to early graduate students of mathematics or theoretical computer science. At the same time, about half of the book consists of material that up until now was only available in original research papers or in various surveys.
]]></description>
<dc:subject>to-read to-cite discrepancy-theory algorithmic-information-theory geometry statistics talking-about-stuff consider:tree-generation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e455b79938f2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-cite"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrepancy-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithmic-information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:talking-about-stuff"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:tree-generation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2405.17919">
    <title>[2405.17919] Fisher's Legacy of Directional Statistics, and Beyond to Statistics on Manifolds</title>
    <dc:date>2024-07-01T14:19:11+00:00</dc:date>
    <link>https://arxiv.org/abs/2405.17919</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[It will not be an exaggeration to say that R A Fisher is the Albert Einstein of Statistics. He pioneered almost all the main branches of statistics, but it is not as well known that he opened the area of Directional Statistics with his 1953 paper introducing a distribution on the sphere which is now known as the Fisher distribution. He stressed that for spherical data one should take into account that the data is on a manifold. We will describe this Fisher distribution and reanalyse his geological data. We also comment on the two goals he set himself in that paper, and how he reinvented the von Mises distribution on the circle. Since then, many extensions of this distribution have appeared bearing Fisher's name such as the von Mises Fisher distribution and the matrix Fisher distribution. In fact, the subject of Directional Statistics has grown tremendously in the last two decades with new applications emerging in Life Sciences, Image Analysis, Machine Learning and so on. We give a recent new method of constructing the Fisher type distribution which has been motivated by some problems in Machine Learning. The subject related to his distribution has evolved since then more broadly as Statistics on Manifolds which also includes the new field of Shape Analysis. We end with a historical note pointing out some correspondence between D'Arcy Thompson and R A Fisher related to Shape Analysis.
]]></description>
<dc:subject>statistics history-of-science directional-statistics probability-theory models-and-modes biography</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:76b988d8705b/</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:history-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:directional-statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biography"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2205.14430">
    <title>[2205.14430] Angle-Uniform Parallel Coordinates</title>
    <dc:date>2024-05-07T11:14:00+00:00</dc:date>
    <link>https://arxiv.org/abs/2205.14430</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present angle-uniform parallel coordinates, a data-independent technique that deforms the image plane of parallel coordinates so that the angles of linear relationships between two variables are linearly mapped along the horizontal axis of the parallel coordinates plot. Despite being a common method for visualizing multidimensional data, parallel coordinates are ineffective for revealing positive correlations since the associated parallel coordinates points of such structures may be located at infinity in the image plane and the asymmetric encoding of negative and positive correlations may lead to unreliable estimations. To address this issue, we introduce a transformation that bounds all points horizontally using an angle-uniform mapping and shrinks them vertically in a structure-preserving fashion; polygonal lines become smooth curves and a symmetric representation of data correlations is achieved. We further propose a combined subsampling and density visualization approach to reduce visual clutter caused by overdrawing. Our method enables accurate visual pattern interpretation of data correlations, and its data-independent nature makes it applicable to all multidimensional datasets. The usefulness of our method is demonstrated using examples of synthetic and real-world datasets.
]]></description>
<dc:subject>data-analysis visualization parallel-coordinates multiobjective-optimization rather-interesting statistics data-science scientific-communication</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5ad8f735baab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:parallel-coordinates"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:scientific-communication"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.04574">
    <title>[1711.04574] Learning Explanatory Rules from Noisy Data</title>
    <dc:date>2022-05-08T11:34:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.04574</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek large amounts of training data---which is not necessarily easily obtained---that sufficiently approximates the data distribution of the domain we wish to test on. In contrast, logic programming methods such as Inductive Logic Programming offer an extremely data-efficient process by which models can be trained to reason on symbolic domains. However, these methods are unable to deal with the variety of domains neural networks can be applied to: they are not robust to noise in or mislabelling of inputs, and perhaps more importantly, cannot be applied to non-symbolic domains where the data is ambiguous, such as operating on raw pixels. In this paper, we propose a Differentiable Inductive Logic framework, which can not only solve tasks which traditional ILP systems are suited for, but shows a robustness to noise and error in the training data which ILP cannot cope with. Furthermore, as it is trained by backpropagation against a likelihood objective, it can be hybridised by connecting it with neural networks over ambiguous data in order to be applied to domains which ILP cannot address, while providing data efficiency and generalisation beyond what neural networks on their own can achieve.
]]></description>
<dc:subject>machine-learning representation rather-interesting statistics automation to-understand consider:genetic-programming consider:graphical-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:36ff028b1ca2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:automation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:graphical-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.02365">
    <title>[2102.02365] Wind Field Reconstruction with Adaptive Random Fourier Features</title>
    <dc:date>2022-04-19T10:30:54+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.02365</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We investigate the use of spatial interpolation methods for reconstructing the horizontal near-surface wind field given a sparse set of measurements. In particular, random Fourier features is compared to a set of benchmark methods including Kriging and Inverse distance weighting. Random Fourier features is a linear model β(xx)=∑Kk=1βkeiωkxx approximating the velocity field, with frequencies ωk randomly sampled and amplitudes βk trained to minimize a loss function. We include a physically motivated divergence penalty term |∇⋅β(xx)|2, as well as a penalty on the Sobolev norm. We derive a bound on the generalization error and derive a sampling density that minimizes the bound. Following (arXiv:2007.10683 [math.NA]), we devise an adaptive Metropolis-Hastings algorithm for sampling the frequencies of the optimal distribution. In our experiments, our random Fourier features model outperforms the benchmark models.
]]></description>
<dc:subject>approximation inverse-problems rather-interesting learning-from-data nonlinear-dynamics online-learning to-understand statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3fa7289011de/</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:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2010.05170">
    <title>[2010.05170] What causes the test error? Going beyond bias-variance via ANOVA</title>
    <dc:date>2022-04-09T12:06:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2010.05170</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Modern machine learning methods are often overparametrized, allowing adaptation to the data at a fine level. This can seem puzzling; in the worst case, such models do not need to generalize. This puzzle inspired a great amount of work, arguing when overparametrization reduces test error, in a phenomenon called "double descent". Recent work aimed to understand in greater depth why overparametrization is helpful for generalization. This leads to discovering the unimodality of variance as a function of the level of parametrization, and to decomposing the variance into that arising from label noise, initialization, and randomness in the training data to understand the sources of the error. 
In this work we develop a deeper understanding of this area. Specifically, we propose using the analysis of variance (ANOVA) to decompose the variance in the test error in a symmetric way, for studying the generalization performance of certain two-layer linear and non-linear networks. The advantage of the analysis of variance is that it reveals the effects of initialization, label noise, and training data more clearly than prior approaches. Moreover, we also study the monotonicity and unimodality of the variance components. While prior work studied the unimodality of the overall variance, we study the properties of each term in variance decomposition. 
One key insight is that in typical settings, the interaction between training samples and initialization can dominate the variance; surprisingly being larger than their marginal effect. Also, we characterize "phase transitions" where the variance changes from unimodal to monotone. On a technical level, we leverage advanced deterministic equivalent techniques for Haar random matrices, that -- to our knowledge -- have not yet been used in the area. We also verify our results in numerical simulations and on empirical data examples.
]]></description>
<dc:subject>machine-learning statistics bias-variance rather-interesting to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5d9faced6f7c/</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:bias-variance"/>
	<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/2203.06498">
    <title>[2203.06498] The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning</title>
    <dc:date>2022-04-02T12:26:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.06498</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent concerns that machine learning (ML) may be facing a reproducibility and replication crisis suggest that some published claims in ML research cannot be taken at face value. These concerns inspire analogies to the replication crisis affecting the social and medical sciences, as well as calls for greater integration of statistical approaches to causal inference and predictive modeling. A deeper understanding of what reproducibility concerns in research in supervised ML have in common with the replication crisis in experimental science can put the new concerns in perspective, and help researchers avoid "the worst of both worlds" that can emerge when ML researchers begin borrowing methodologies from explanatory modeling without understanding their limitations, and vice versa. We contribute a comparative analysis of concerns about inductive learning that arise in different stages of the modeling pipeline in causal attribution as exemplified in psychology versus predictive modeling as exemplified by ML. We identify themes that re-occur in reform discussions like overreliance on asymptotic theory and non-credible beliefs about real-world data generating processes. We argue that in both fields, claims from learning are implied to generalize outside the specific environment studied (e.g., the input dataset or subject sample, modeling implementation, etc.) but are often impossible to refute due to forms of underspecification. In particular, many errors being acknowledged in ML expose cracks in long-held beliefs that optimizing predictive accuracy using huge datasets absolves one from having to make assumptions about the underlying data generating process. We conclude by discussing rhetorical risks like error misdiagnosis that arise in times of methodological uncertainty.
]]></description>
<dc:subject>via:cshalizi statistics machine-learning reproducibility science-studies models-and-modes assumptions rather-interesting consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6d5f50bf1656/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reproducibility"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:science-studies"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:assumptions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<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/2202.02842">
    <title>[2202.02842] Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data</title>
    <dc:date>2022-02-11T23:58:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.02842</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The search for effective and robust generalization metrics has been the focus of recent theoretical and empirical work. 
In this paper, we discuss the performance of natural language processing (NLP) models, and we evaluate various existing and novel generalization metrics. 
Compared to prior studies, we 
(i) focus on NLP instead of computer vision (CV), 
(ii) focus on generalization metrics that predict test error instead of the generalization gap, 
(iii) focus on generalization metrics that do not need the access to data, and 
(iv) focus on the heavy-tail (HT) phenomenon that has received comparatively less attention in the study of deep neural networks (NNs). 
We extend recent HT-based work which focuses on power law (PL) distributions, and we study exponential (EXP) and exponentially truncated power law (E-TPL) fitting to the empirical spectral densities (ESDs) of weight matrices. 
Our detailed empirical studies show that 
(i) \emph{shape metrics}, or the metrics obtained from fitting the shape of the ESDs, perform uniformly better at predicting generalization performance than \emph{scale metrics} commonly studied in the literature, as measured by the \emph{average} rank correlations with the generalization performance for all of our experiments; 
(ii) among forty generalization metrics studied in our paper, the \RANDDISTANCE metric, a new shape metric invented in this paper that measures the distance between empirical eigenvalues of weight matrices and those of randomly initialized weight matrices, achieves the highest worst-case rank correlation with generalization performance under a variety of training settings; and 
(iii) among the three HT distributions considered in our paper, the E-TPL fitting of ESDs performs the most robustly.
]]></description>
<dc:subject>via:cshalizi statistics generalization estimation rather-interesting consider:related-measures-for-GP to-understand to-forward</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:135e89afbf33/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:related-measures-for-GP"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-forward"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.10168">
    <title>[1804.10168] BEST : A decision tree algorithm that handles missing values</title>
    <dc:date>2022-01-29T12:52:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.10168</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The main contribution of this paper is the development of a new decision tree algorithm. The proposed approach allows users to guide the algorithm through the data partitioning process. We believe this feature has many applications but in this paper we demonstrate how to utilize this algorithm to analyse data sets containing missing values. We tested our algorithm against simulated data sets with various missing data structures and a real data set. The results demonstrate that this new classification procedure efficiently handles missing values and produces results that are slightly more accurate and more interpretable than most common procedures without any imputations or pre-processing.
]]></description>
<dc:subject>decision-trees statistics machine-learning rather-interesting missing-values data-analysis to-write-about to-understand consider:symbolic-regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a8fdaa105b2e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:decision-trees"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<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:missing-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.04103">
    <title>[2104.04103] Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters</title>
    <dc:date>2022-01-24T13:56:01+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.04103</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Causal decision making (CDM) based on machine learning has become a routine part of business. Businesses algorithmically target offers, incentives, and recommendations to affect consumer behavior. Recently, we have seen an acceleration of research related to CDM and causal effect estimation (CEE) using machine-learned models. This article highlights an important perspective: CDM is not the same as CEE, and counterintuitively, accurate CEE is not necessary for accurate CDM. Our experience is that this is not well understood by practitioners or most researchers. Technically, the estimand of interest is different, and this has important implications both for modeling and for the use of statistical models for CDM. We draw on prior research to highlight three implications. (1) We should consider carefully the objective function of the causal machine learning, and if possible, optimize for accurate treatment assignment rather than for accurate effect-size estimation. (2) Confounding does not have the same effect on CDM as it does on CEE. The upshot is that for supporting CDM it may be just as good or even better to learn with confounded data as with unconfounded data. Finally, (3) causal statistical modeling may not be necessary to support CDM because a proxy target for statistical modeling might do as well or better. This third observation helps to explain at least one broad common CDM practice that seems wrong at first blush: the widespread use of non-causal models for targeting interventions. The last two implications are particularly important in practice, as acquiring (unconfounded) data on all counterfactuals can be costly and often impracticable. These observations open substantial research ground. We hope to facilitate research in this area by pointing to related articles from multiple contributing fields, including two dozen articles published the last three to four years.
]]></description>
<dc:subject>machine-learning inference estimation rather-interesting statistics explanation models to-understand to-write-about consider:regression-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:41a5a6c5e959/</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:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<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:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:regression-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tidyverse.org/learn/">
    <title>Learn the tidyverse</title>
    <dc:date>2021-12-11T11:18:31+00:00</dc:date>
    <link>https://www.tidyverse.org/learn/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The best place to start learning the tidyverse is R for Data Science (R4DS for short), an O’Reilly book written by Hadley Wickham and Garrett Grolemund. It’s designed to take you from knowing nothing about R or the tidyverse to having all the basic tools of data science at your fingertips. You can read it online for free, or buy a physical copy.

We highly recommend pairing R4DS with the RStudio cheatsheets. These cheatsheets have been carefully designed to pack a lot of information into a small amount of space. You can keep them handy at your desk and quickly jog your memory when you get stuck. Most of the cheatsheets have been translated into multiple languages.

]]></description>
<dc:subject>R tidyverse statistics software framework</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a79faed5783d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:R"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tidyverse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:framework"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.04157">
    <title>[1703.04157] Using Aggregated Relational Data to feasibly identify network structure without network data</title>
    <dc:date>2021-11-04T12:54:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.04157</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Social network data is often prohibitively expensive to collect, limiting empirical network research. Typical economic network mapping requires (1) enumerating a census, (2) eliciting the names of all network links for each individual, (3) matching the list of social connections to the census, and (4) repeating (1)-(3) across many networks. In settings requiring field surveys, steps (2)-(3) can be very expensive. In other network populations such as financial intermediaries or high-risk groups, proprietary data and privacy concerns may render (2)-(3) impossible. Both restrict the accessibility of high-quality networks research to investigators with considerable resources. 
We propose an inexpensive and feasible strategy for network elicitation using Aggregated Relational Data (ARD) -- responses to questions of the form "How many of your social connections have trait k?" Our method uses ARD to recover the parameters of a general network formation model, which in turn, permits the estimation of any arbitrary node- or graph-level statistic. The method works well in simulations and in matching a range of network characteristics in real-world graphs from 75 Indian villages. Moreover, we replicate the results of two field experiments that involved collecting network data. We show that the researchers would have drawn similar conclusions using ARD alone. Finally, using calculations from J-PAL fieldwork, we show that in rural India, for example, ARD surveys are 80% cheaper than full network surveys.
]]></description>
<dc:subject>statistics network-theory social-networks inverse-problems rather-interesting to-write-about to-simulate consider:visualization consider:privacy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7171afe1aa06/</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:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<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:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:privacy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tidyverse.org/">
    <title>Tidyverse</title>
    <dc:date>2021-10-28T14:23:31+00:00</dc:date>
    <link>https://www.tidyverse.org/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The tidyverse is an opinionated collection of R packages designed for data science. All packages share an underlying design philosophy, grammar, and data structures.

]]></description>
<dc:subject>R data-analysis software-development-is-not-programming to-understand library statistics visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f35f64dd76b2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:R"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-development-is-not-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2010.15662">
    <title>[2010.15662] Independence Tests Without Ground Truth for Noisy Learners</title>
    <dc:date>2021-10-03T13:13:29+00:00</dc:date>
    <link>https://arxiv.org/abs/2010.15662</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Exact ground truth invariant polynomial systems can be written for arbitrarily correlated binary classifiers. Their solutions give estimates for sample statistics that require knowledge of the ground truth of the correct labels in the sample. Of these polynomial systems, only a few have been solved in closed form. Here we discuss the exact solution for independent binary classifiers - resolving an outstanding problem that has been presented at this conference and others. Its practical applicability is hampered by its sole remaining assumption - the classifiers need to be independent in their sample errors. We discuss how to use the closed form solution to create a self-consistent test that can validate the independence assumption itself absent the correct labels ground truth. It can be cast as an algebraic geometry conjecture for binary classifiers that remains unsolved. A similar conjecture for the ground truth invariant algebraic system for scalar regressors is solvable, and we present the solution here. We also discuss experiments on the Penn ML Benchmark classification tasks that provide further evidence that the conjecture may be true for the polynomial system of binary classifiers.
]]></description>
<dc:subject>machine-learning statistics rather-interesting to-understand classification wisdom-of-crowds</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9f4d24746fab/</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:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wisdom-of-crowds"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2005.00497">
    <title>[2005.00497] The Grammar of Interactive Explanatory Model Analysis</title>
    <dc:date>2021-08-01T12:06:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2005.00497</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? It turns out that this is an ill-posed question. One cannot sufficiently explain a black-box machine learning model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, which inevitably leads to wrong or simplistic reasoning. This problem is known as the Rashomon effect and refers to diverse, even contradictory interpretations of the same phenomenon. Surprisingly, the majority of methods developed for explainable machine learning focus on a single aspect of the model behavior. In contrast, we showcase the problem of explainability as an interactive and sequential analysis of a model. This paper presents how different Explanatory Model Analysis (EMA) methods complement each other and why it is essential to juxtapose them together. The introduced process of Interactive EMA (IEMA) derives from the algorithmic side of explainable machine learning and aims to embrace ideas developed in cognitive sciences. We formalize the grammar of IEMA to describe potential human-model dialogues. IEMA is implemented in the human-centered framework that adopts interactivity, customizability and automation as its main traits. Combined, these methods enhance the responsible approach to predictive modeling.
]]></description>
<dc:subject>machine-learning the-mangle-in-practice rather-interesting explainability user-experience interactivity statistics data-analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:52f512d386c1/</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:the-mangle-in-practice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:explainability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:user-experience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interactivity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://openintro-ims.netlify.app/index.html">
    <title>Welcome to IMS | Introduction to Modern Statistics</title>
    <dc:date>2021-07-22T09:33:39+00:00</dc:date>
    <link>https://openintro-ims.netlify.app/index.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This is the website for Introduction to Modern Statistics, First Edition by Mine Çetinkaya-Rundel and Johanna Hardin. Introduction to Modern Statistics, which we’ll refer to as IMS going forward, is a textbook from the OpenIntro project.

The book will always be available for free here. It is also available in PDF (for free or for the amount you choose to donate to the OpenIntro project) on Leanpub and in black&white paperback for purchase for $20. 
]]></description>
<dc:subject>book statistics open-access rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:362c24ecafa5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:book"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-access"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2103.10357">
    <title>[2103.10357] The equidistribution of some Mahonian statistics over permutations avoiding a pattern of length three</title>
    <dc:date>2021-07-08T10:42:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2103.10357</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We prove the equidistribution of several multistatistics over some classes of permutations avoiding a 3-length pattern. We deduce the equidistribution, on the one hand of inv and foze" statistics, and on the other hand that of maj and makl statistics, over these classes of pattern avoiding permutations. Here inv and maj are the celebrated Mahonian statistics, foze" is one of the statistics defined in terms of generalized patterns in the 2000 pioneering paper of Babson and Steingrímsson, and makl is one of the statistics defined by Clarke, Steingrímsson and Zeng in 1997. These results solve several conjectures posed by Amini in 2018.
]]></description>
<dc:subject>permutations combinatorics enumeration statistics looking-to-see rather-interesting consider:local-statistics consider:sequence-labeling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c1e93fe7f895/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:permutations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:enumeration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:local-statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:sequence-labeling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.09588">
    <title>[2004.09588] On The Problem of Relevance in Statistical Inference</title>
    <dc:date>2021-07-08T10:38:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.09588</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper is dedicated to the "50 Years of the Relevance Problem" - a long-neglected topic that begs attention from practical statisticians who are concerned with the problem of drawing inference from large-scale heterogeneous data.
]]></description>
<dc:subject>philosophy-of-engineering statistics rather-interesting machine-learning modeling-is-not-mathematics to-write-about to-simulate consider:symbolic-regression consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8824aa82fd47/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
	<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:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
	<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/2012.11870">
    <title>[2012.11870] A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem</title>
    <dc:date>2021-05-09T11:40:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.11870</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The problem of class imbalance is extensive for focusing on numerous applications in the real world. In such a situation, nearly all of the examples are labeled as one class called majority class, while far fewer examples are labeled as the other class usually, the more important class is called minority. Over the last few years, several types of research have been carried out on the issue of class imbalance, including data sampling, cost-sensitive analysis, Genetic Programming based models, bagging, boosting, etc. Nevertheless, in this survey paper, we enlisted the 24 related studies in the years 2003, 2008, 2010, 2012 and 2014 to 2019, focusing on the architecture of single, hybrid, and ensemble method design to understand the current status of improving classification output in machine learning techniques to fix problems with class imbalances. This survey paper also includes a statistical analysis of the classification algorithms under various methods and several other experimental conditions, as well as datasets used in different research papers.
]]></description>
<dc:subject>statistics data-balancing classification synthetic-data rather-interesting performance-measure to-write-about consider:sampling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:32c0c43af08e/</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:data-balancing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:synthetic-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:sampling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/10.1101/2021.02.16.431544v1">
    <title>A test statistic to quantify treelikeness in phylogenetics | bioRxiv</title>
    <dc:date>2021-03-12T14:35:15+00:00</dc:date>
    <link>https://www.biorxiv.org/content/10.1101/2021.02.16.431544v1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Most phylogenetic analyses assume that the evolutionary history of an alignment (either that of a single locus, or of multiple concatenated loci) can be described by a single bifurcating tree, the so-called the treelikeness assumption. Treelikeness can be violated by biological events such as recombination, introgression, or incomplete lineage sorting, and by systematic errors in phylogenetic analyses. The incorrect assumption of treelikeness may then mislead phylogenetic inferences. To quantify and test for treelikeness in alignments, we develop a test statistic which we call the tree proportion. This statistic quantifies the proportion of the edge weights in a phylogenetic network that are represented in a bifurcating phylogenetic tree of the same alignment. We extend this statistic to a statistical test of treelikeness using a parametric bootstrap. We use extensive simulations to compare tree proportion to a range of related approaches. We show that tree proportion successfully identifies non-treelikeness in a wide range of simulation scenarios, and discuss its strengths and weaknesses compared to other approaches. The power of the tree-proportion test to reject non-treelike alignments can be lower than some other approaches, but these approaches tend to be limited in their scope and/or the ease with which they can be interpreted. Our recommendation is to test treelikeness of sequence alignments with both tree proportion and mosaic methods such as 3Seq. The scripts necessary to replicate this study are available at https://github.com/caitlinch/treelikeness

]]></description>
<dc:subject>statistics rather-interesting phylogenetics models-and-modes fittedness-of-hypotheses to-write-about consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:36a478f66aaf/</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:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:phylogenetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fittedness-of-hypotheses"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://picturethismaths.wordpress.com/2021/02/03/three-correlations-and-other-statistical-models/">
    <title>Three correlations and other statistical models – Picture this maths</title>
    <dc:date>2021-03-03T14:31:43+00:00</dc:date>
    <link>https://picturethismaths.wordpress.com/2021/02/03/three-correlations-and-other-statistical-models/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In my previous post we saw how the above shape (called the elliptope, or the samosa) shows up when looking at correlations between three variables. The samosa is all points  that are a triple of correlations of three variables. For example,  is in the samosa, because it is possible to have three variables with all correlations 0.5. But  is not, because if two variables have perfect correlation with a third, they must also be perfectly correlated.

]]></description>
<dc:subject>visualization rather-interesting statistics correlation constraint-satisfaction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4132f629ffb2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<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:correlation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://pair-code.github.io/lit/">
    <title>Language Interpretability Tool</title>
    <dc:date>2020-11-17T22:50:09+00:00</dc:date>
    <link>https://pair-code.github.io/lit/</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>via:twitter rather-interesting natural-language-processing visualization statistics library to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d24060bf7770/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:twitter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.07801">
    <title>[1906.07801] Safe Testing</title>
    <dc:date>2020-10-13T21:00:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.07801</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We develop the theory of hypothesis testing based on the e-value, a notion of evidence that, unlike the p-value, allows for effortlessly combining results from several tests. Even in the common scenario of optional continuation, where the decision to perform a new test depends on previous test outcomes, 'safe' tests based on e-values generally preserve Type-I error guarantees. Our main result shows that e-values exist for completely general testing problems with composite null and alternatives. Their prime interpretation is in terms of gambling or investing, each e-value corresponding to a particular investment. Surprisingly, optimal 'GROW' e-values, which lead to fastest capital growth, are fully characterized by the joint information projection (JIPr) between the set of all Bayes marginal distributions on H0 and H1. Thus, optimal e-values also have an interpretation as Bayes factors, with priors given by the JIPr. We illustrate the theory using several 'classic' examples including a one-sample safe t-test and the 2 x 2 contingency table. Sharing Fisherian, Neymanian and Jeffreys-Bayesian interpretations, e-values and safe tests may provide a methodology acceptable to adherents of all three schools.
]]></description>
<dc:subject>statistics hypothesis-testing via:several heuristics to-understand of-unknown-utility academic-culture horse-races</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:38f278bb4f59/</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:hypothesis-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:several"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:of-unknown-utility"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1902.07672">
    <title>[1902.07672] Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems</title>
    <dc:date>2020-07-22T11:21:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1902.07672</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Stochastic Proximal Gradient (SPG) methods have been widely used for solving optimization problems with a simple (possibly non-smooth) regularizer in machine learning and statistics. However, to the best of our knowledge no non-asymptotic convergence analysis of SPG exists for non-convex optimization with a non-smooth and non-convex regularizer. All existing non-asymptotic analysis of SPG for solving non-smooth non-convex problems require the non-smooth regularizer to be a convex function, and hence are not applicable to a non-smooth non-convex regularized problem. This work initiates the analysis to bridge this gap and opens the door to non-asymptotic convergence analysis of non-smooth non-convex regularized problems. We analyze several variants of mini-batch SPG methods for minimizing a non-convex objective that consists of a smooth non-convex loss and a non-smooth non-convex regularizer. Our contributions are two-fold: (i) we show that they enjoy the same complexities as their counterparts for solving convex regularized non-convex problems in terms of finding an approximate stationary point; (ii) we develop more practical variants using dynamic mini-batch size instead of a fixed mini-batch size without requiring the target accuracy level of solution. The significance of our results is that they improve upon the-state-of-art results for solving non-smooth non-convex regularized problems. We also empirically demonstrate the effectiveness of the considered SPG methods in comparison with other peer stochastic methods.
]]></description>
<dc:subject>performance-measure guessing rather-interesting statistics numerical-methods algorithms machine-learning horse-races to-understand to-simulate consider:lexicase consider:comparisons-in-GP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f5aabb982183/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:guessing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<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:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<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:lexicase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:comparisons-in-GP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.03634">
    <title>[1710.03634] LinXGBoost: Extension of XGBoost to Generalized Local Linear Models</title>
    <dc:date>2020-06-13T21:25:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.03634</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[XGBoost is often presented as the algorithm that wins every ML competition. Surprisingly, this is true even though predictions are piecewise constant. This might be justified in high dimensional input spaces, but when the number of features is low, a piecewise linear model is likely to perform better. XGBoost was extended into LinXGBoost that stores at each leaf a linear model. This extension, equivalent to piecewise regularized least-squares, is particularly attractive for regression of functions that exhibits jumps or discontinuities. Those functions are notoriously hard to regress. Our extension is compared to the vanilla XGBoost and Random Forest in experiments on both synthetic and real-world data sets.
]]></description>
<dc:subject>machine-learning numerical-methods curve-fitting statistics to-understand to-write-about consider:genetic-programming consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:74ae28f026fc/</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:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:curve-fitting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</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://www.knowablemagazine.org/article/health-disease/2020/single-subject-design">
    <title>N of 1: Singular science</title>
    <dc:date>2020-05-03T13:18:02+00:00</dc:date>
    <link>https://www.knowablemagazine.org/article/health-disease/2020/single-subject-design</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A study of one person — also called an N of 1 trial — can uncover subtle, important results that would be lost in a large-scale study, says geneticist Nicholas Schork of the Translational Genomics Research Institute in Phoenix. The results, he says, can be combined to provide insights for the population at large. But with N of 1 studies, the individual matters above all. “People differ at fundamental levels,” says Schork, who discussed the potential of N of 1 studies in a 2017 issue of the Annual Review of Nutrition. And the only way to understand individuals is to study them.

]]></description>
<dc:subject>experimental-design medical-technology clinical-trials rather-interesting casuistical-science statistics to-understand to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8f275dc83713/</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:medical-technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clinical-trials"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:casuistical-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf: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://arxiv.org/abs/1909.06485">
    <title>[1909.06485] Multi-Perspective, Simultaneous Embedding</title>
    <dc:date>2020-05-02T15:37:24+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.06485</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We describe a method for simultaneous visualization of multiple pairwise distances in 3 dimensional (3D) space. Given the distance matrices that correspond to 2 dimensional projections of a 3 dimensional object (dataset) the goal is to recover the 3 dimensional object (dataset). We propose an approach that uses 3D to place the points, along with projections (planes) that preserve each of the given distance matrices. Our multi-perspective, simultaneous embedding (MPSE) method is based on non-linear dimensionality reduction that generalizes multidimensional scaling. We consider two versions of the problem: in the first one we are given the input distance matrices and the projections (e.g., if we have 3 different projections we can use the three orthogonal directions of the unit cube). In the second version of the problem we also compute the best projections as part of the optimization. We experimentally evaluate MPSE using synthetic datasets that illustrate the quality of the resulting solutions. Finally, we provide a functional prototype which implements both settings.
]]></description>
<dc:subject>dimension-reduction projection statistics algorithms rather-interesting to-simulate to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:20aafaa21714/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:projection"/>
	<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:to-simulate"/>
	<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/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.biorxiv.org/content/10.1101/393835v1">
    <title>Regularization Improves the Robustness of Learned Sequence-to-Expression Models | bioRxiv</title>
    <dc:date>2020-02-18T22:52:54+00:00</dc:date>
    <link>https://www.biorxiv.org/content/10.1101/393835v1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding of the gene regulatory activity of enhancers is a major problem in regulatory biology. The nascent field of sequence-to-expression modelling seeks to create quantitative models of gene expression based on regulatory DNA (cis) and cellular environmental (trans) contexts. All quantitative models are defined partially by numerical parameters, and it is common to fit these parameters to data provided by existing experimental results. However, the relative paucity of experimental data appropriate for this task, and lacunae in our knowledge of all components of the systems, results in problems often being under-specified, which in turn may lead to a situation where wildly different model parameterizations perform similarly well on training data. It may also lead to models being fit to the idiosyncrasies of the training data, without representing the more general process (overfitting).

In other contexts where parameter-fitting is performed, it is common to apply regularization to reduce overfitting. We systematically evaluated the efficacy of three types of regularization in improving the generalizability of trained sequence-to-expression models. The evaluation was performed in two types of cross-validation experiments: one training on D. melanogaster data and predicting on orthologous enhancers from related species, and the other cross-validating between four D. melanogaster neurogenic ectoderm enhancers, which are thought to be under control of the same transcription factors. We show that training with a combination of noise-injection, L1, and L2 regularization can drastically reduce overfitting and improve the generalizability of learned sequence-to-expression models. These results suggest that it may be possible to mitigate the tendency of sequence-to-expression models to overfit available data, thus improving predictive power and potentially resulting in models that provide better insight into underlying biological processes.

]]></description>
<dc:subject>bioinformatics systems-biology nonlinear-dynamics machine-learning regularization statistics numerical-methods heuristics to-write-about to-simulate consider:symbolic-regression consider:robustness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f08dfb1849d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:regularization"/>
	<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:heuristics"/>
	<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:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.johndcook.com/blog/2018/05/11/two-sample-t-test/">
    <title>Robustness of the two-sample t-test</title>
    <dc:date>2020-02-12T12:24:40+00:00</dc:date>
    <link>https://www.johndcook.com/blog/2018/05/11/two-sample-t-test/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[It is fairly well known that the t-test is robust to departures from a normal distribution, as long as the actual distribution is symmetric. That is, the test works more or less as advertised as long as the distribution is symmetric like a normal distribution, but it may not work as expected if the distribution is asymmetric.

This post will explore the robustness of the t-test via simulation. How far can you be from a normal distribution and still do OK? Can you have any distribution as long as it’s symmetric? Does a little asymmetry ruin everything? If something does go wrong, how does it go wrong?

]]></description>
<dc:subject>statistics looking-to-see rather-interesting algorithms robustness to-do to-write-about consider:animation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dd64efe38689/</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:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:animation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.05163">
    <title>[1812.05163] Declination as a Metric to Detect Partisan Gerrymandering</title>
    <dc:date>2020-01-27T23:32:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.05163</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We explore the Declination, a new metric intended to detect partisan gerrymandering. We consider instances in which each district has equal turnout, the maximum turnout to minimum turnout is bounded, and turnout is unrestricted. For each of these cases, we show exactly which vote-share, seat-share pairs (V,S) have an election outcome with Declination equal to 0. We also show how our analyses can be applied to finding vote-share, seat-share pairs that are possible for nonzero Declination. 
Within our analyses, we show that Declination cannot detect all forms of packing and cracking, and we compare the Declination to the Efficiency Gap. We show that these two metrics can behave quite differently, and give explicit examples of that occurring.
]]></description>
<dc:subject>statistics politics gerrymandering cultural-engineering rather-interesting performance-measure to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:76021792de5c/</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:politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gerrymandering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cultural-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1203.3353">
    <title>[1203.3353] Solving Structure with Sparse, Randomly-Oriented X-ray Data</title>
    <dc:date>2020-01-19T15:45:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1203.3353</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Single-particle imaging experiments of biomolecules at x-ray free-electron lasers (XFELs) require processing of hundreds of thousands (or more) of images that contain very few x-rays. Each low-flux image of the diffraction pattern is produced by a single, randomly oriented particle, such as a protein. We demonstrate the feasibility of collecting data at these extremes, averaging only 2.5 photons per frame, where it seems doubtful there could be information about the state of rotation, let alone the image contrast. This is accomplished with an expectation maximization algorithm that processes the low-flux data in aggregate, and without any prior knowledge of the object or its orientation. The versatility of the method promises, more generally, to redefine what measurement scenarios can provide useful signal in the high-noise regime.
]]></description>
<dc:subject>diffraction inverse-problems tomography rather-interesting algorithms statistics probability-theory inference to-simulate to-write-about optimization signal-processing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3aebefbb9649/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:diffraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tomography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1601.00670">
    <title>[1601.00670] Variational Inference: A Review for Statisticians</title>
    <dc:date>2020-01-08T13:32:44+00:00</dc:date>
    <link>https://arxiv.org/abs/1601.00670</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this paper, we review variational inference (VI), a method from machine learning that approximates probability densities through optimization. VI has been used in many applications and tends to be faster than classical methods, such as Markov chain Monte Carlo sampling. The idea behind VI is to first posit a family of densities and then to find the member of that family which is close to the target. Closeness is measured by Kullback-Leibler divergence. We review the ideas behind mean-field variational inference, discuss the special case of VI applied to exponential family models, present a full example with a Bayesian mixture of Gaussians, and derive a variant that uses stochastic optimization to scale up to massive data. We discuss modern research in VI and highlight important open problems. VI is powerful, but it is not yet well understood. Our hope in writing this paper is to catalyze statistical research on this class of algorithms.
]]></description>
<dc:subject>machine-learning statistics feature-construction to-understand algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a9506f15084e/</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:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1905.13195">
    <title>[1905.13195] Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections</title>
    <dc:date>2019-12-29T10:59:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.13195</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal distribution or other distribution encouraging sparsity. However, this prior is agnostic to the generative process of the input data, which might lead to unwarranted generalization for out-of-distribution tested data. We suggest the presence of a confounder for the relation between the input data and the discriminative function given the target label. We propose an approach for modeling this confounder by sharing neural connectivity patterns between the generative and discriminative networks. This approach leads to a new deep architecture, where networks are sampled from the posterior of local causal structures, and coupled into a compact hierarchy. We demonstrate that sampling networks from this hierarchy, proportionally to their posterior, is efficient and enables estimating various types of uncertainties. Empirical evaluations of our method demonstrate significant improvement compared to state-of-the-art calibration and out-of-distribution detection methods.
]]></description>
<dc:subject>machine-learning statistics meta-modeling feature-construction model-interrogation neural-networks to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3c545592d68d/</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:meta-modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:model-interrogation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.01248">
    <title>[1906.01248] The density and minimal gap of visible points in some planar quasicrystals</title>
    <dc:date>2019-12-29T10:29:24+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.01248</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We give formulas for the density of visible points of several families of planar quasicrystals, which include the Ammann-Beenker point set and vertex sets of some rhombic Penrose tilings. These densities are used in order to calculate the limiting minimal normalised gap between the angles of visible points in two families of planar quasicrystals, which include the Ammann-Beenker point set and vertex sets of some rhombic Penrose tilings.
]]></description>
<dc:subject>plane-geometry tiling quasicrystals aperiodic-tiling looking-to-see visibility-problems statistics to-simulate to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:68b6121b254f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:plane-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tiling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quasicrystals"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aperiodic-tiling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visibility-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.02987">
    <title>[1812.02987] Time Series Featurization via Topological Data Analysis</title>
    <dc:date>2019-11-25T23:25:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.02987</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We develop a novel algorithm for feature extraction in time series data by leveraging tools from topological data analysis. Our algorithm provides a simple, efficient way to successfully harness topological features of the attractor of the underlying dynamical system for an observed time series. The proposed methodology relies on the persistent landscapes and silhouette of the Rips complex obtained after a de-noising step based on principal components applied to a time-delayed embedding of a noisy, discrete time series sample. We analyze the stability properties of the proposed approach and show that the resulting TDA-based features are robust to sampling noise. Experiments on synthetic and real-world data demonstrate the effectiveness of our approach. We expect our method to provide new insights on feature extraction from granular, noisy time series data.
]]></description>
<dc:subject>time-series feature-construction feature-extraction topology statistics heuristics numerical-methods to-understand to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:911c6fb3332d/</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:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:topology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.10140">
    <title>[1909.10140] A new coefficient of correlation</title>
    <dc:date>2019-11-23T12:50:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.10140</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Is it possible to define a coefficient of correlation which is (a) as simple as the classical coefficients like Pearson's correlation or Spearman's correlation, and yet (b) consistently estimates some simple and interpretable measure of the degree of dependence between the variables, which is 0 if and only if the variables are independent and 1 if and only if one is a measurable function of the other, and (c) has a simple asymptotic theory under the hypothesis of independence, like the classical coefficients? This article answers this question in the affirmative, by producing such a coefficient. No assumptions are needed on the distributions of the variables. There are several coefficients in the literature that converge to 0 if and only if the variables are independent, but none that satisfy any of the other properties mentioned above.
]]></description>
<dc:subject>statistics probability-theory performance-measure rather-interesting nudge-targets to-write-about to-replicate consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9623577ab990/</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:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-replicate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1612.02487">
    <title>[1612.02487] Interactive Elicitation of Knowledge on Feature Relevance Improves Predictions in Small Data Sets</title>
    <dc:date>2019-10-26T12:45:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1612.02487</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Providing accurate predictions is challenging for machine learning algorithms when the number of features is larger than the number of samples in the data. Prior knowledge can improve machine learning models by indicating relevant variables and parameter values. Yet, this prior knowledge is often tacit and only available from domain experts. We present a novel approach that uses interactive visualization to elicit the tacit prior knowledge and uses it to improve the accuracy of prediction models. The main component of our approach is a user model that models the domain expert's knowledge of the relevance of different features for a prediction task. In particular, based on the expert's earlier input, the user model guides the selection of the features on which to elicit user's knowledge next. The results of a controlled user study show that the user model significantly improves prior knowledge elicitation and prediction accuracy, when predicting the relative citation counts of scientific documents in a specific domain.
]]></description>
<dc:subject>data-analysis statistics user-experience the-mangle-in-practice rather-interesting artificial-colleagues asking-for-help to-understand to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:19f278ff77bc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:user-experience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-mangle-in-practice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-colleagues"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:asking-for-help"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1405.0825">
    <title>[1405.0825] The average representation - a cornucopia of power indices?</title>
    <dc:date>2019-10-13T12:47:14+00:00</dc:date>
    <link>https://arxiv.org/abs/1405.0825</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[For the classical power indices there is a disproportion between power and relative weights, in general. We introduce two new indices, based on weighted representations, which are proportional to suitable relative weights and which also share several important properties of the classical power indices. Imposing further restrictions on the set of representations may lead to a whole family of such indices.
]]></description>
<dc:subject>mechanism-design game-theory aggregation rather-interesting statistics to-write-about to-simulate consider:sampling voting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1fcc583f5849/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mechanism-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aggregation"/>
	<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: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:sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:voting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1902.00415">
    <title>[1902.00415] Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation</title>
    <dc:date>2019-09-28T10:47:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1902.00415</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on {\it mixture distributions} that arise naturally in several application domains where the data contains different sub-populations. For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions. Thus, even if two mixture distributions have identical mixture components but different mixture proportions, the Wasserstein distance between them will be large. This often leads to undesired results in distance-based learning methods for mixture distributions. In this paper, we resolve this issue by introducing {\it Normalized Wasserstein} distance. The key idea is to introduce mixture proportions as optimization variables, effectively normalizing mixture proportions in the Wasserstein formulation. Using the proposed normalized Wasserstein distance, instead of the vanilla one, leads to significant gains working with mixture distributions with imbalanced mixture proportions. We demonstrate effectiveness of the proposed distance in GANs, domain adaptation, adversarial clustering and hypothesis testing over mixture of Gaussians, MNIST, CIFAR-10, CelebA and VISDA datasets.
]]></description>
<dc:subject>statistics distance metrics performance-measure numerical-methods dimension-reduction to-understand machine-learning to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5cc0f0836a46/</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:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.10140#">
    <title>[1909.10140] A new coefficient of correlation</title>
    <dc:date>2019-09-28T10:45:13+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.10140#</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Is it possible to define a coefficient of correlation which is (a) as simple as the classical coefficients like Pearson's correlation or Spearman's correlation, and yet (b) consistently estimates some simple and interpretable measure of the degree of dependence between the variables, which is 0 if and only if the variables are independent and 1 if and only if one is a measurable function of the other, and (c) has a simple asymptotic theory under the hypothesis of independence, like the classical coefficients? This article answers this question in the affirmative, by producing such a coefficient. No assumptions are needed on the distributions of the variables. There are several coefficients in the literature that converge to 0 if and only if the variables are independent, but none that satisfy any of the other properties mentioned above.
]]></description>
<dc:subject>statistics algorithms rather-interesting engineering-design performance-measure define-your-terms to-simulate to-write-about consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:56410294020d/</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:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<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:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.05740">
    <title>[1808.05740] Extremality, Stationarity and Generalized Separation of Collections of Sets</title>
    <dc:date>2019-09-25T10:31:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.05740</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The core arguments used in various proofs of the extremal principle and its extensions as well as in primal and dual characterizations of approximate stationarity and transversality of collections of sets are exposed, analyzed and refined, leading to a unifying theory, encompassing all existing approaches to obtaining 'extremal' statements. For that, we examine and clarify quantitative relationships between the parameters involved in the respective definitions and statements. Some new characterizations of extremality properties are obtained.
]]></description>
<dc:subject>statistics clustering extreme-values to-understand discrimination algorithms rather-odd rather-general-sounding optimization probability-theory consider:weird-GP-stuff</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d7f86b2621f8/</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:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-odd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-general-sounding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:weird-GP-stuff"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.09139">
    <title>[1903.09139] Harmless interpolation of noisy data in regression</title>
    <dc:date>2019-09-22T12:03:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.09139</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solutions that minimize training error interpolate the data, including noise. We characterize the fundamental generalization (mean-squared) error of any interpolating solution in the presence of noise, and show that this error decays to zero with the number of features. Thus, overparameterization can be explicitly beneficial in ensuring harmless interpolation of noise. We discuss two root causes for poor generalization that are complementary in nature -- signal "bleeding" into a large number of alias features, and overfitting of noise by parsimonious feature selectors. For the sparse linear model with noise, we provide a hybrid interpolating scheme that mitigates both these issues and achieves order-optimal MSE over all possible interpolating solutions.
]]></description>
<dc:subject>statistics models performance-measure interpolation rather-interesting to-write-about consider:symbolic-regression consider:aggregate-model-performance consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a33df4020411/</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:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpolation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:aggregate-model-performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://publications.mfo.de/handle/mfo/1410">
    <title>On radial basis functions</title>
    <dc:date>2019-09-19T22:32:43+00:00</dc:date>
    <link>https://publications.mfo.de/handle/mfo/1410</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Many sciences and other areas of research and applications
 from engineering to economics require the approximation
 of functions that depend on many variables.
 This can be for a variety of reasons. Sometimes
 we have a discrete set of data points and we
 want to find an approximating function that completes
 this data; another possibility is that precise
 functions are either not known or it would take too
 long to compute them explicitly. In this snapshot
 we want to introduce a particular method of approximation
 which uses functions called radial basis functions.
 This method is particularly useful when approximating
 functions that depend on very many variables.
 We describe the basic approach to approximation
 with radial basis functions, including their computation,
 give several examples of such functions and
 show some applications.
]]></description>
<dc:subject>statistics explainer numerical-methods models rather-interesting to-write-about to-simulate consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5575de5201d4/</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:explainer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<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/1202.2395">
    <title>[1202.2395] A two parameter ratio-product-ratio estimator using auxiliary information</title>
    <dc:date>2019-09-08T11:44:33+00:00</dc:date>
    <link>https://arxiv.org/abs/1202.2395</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a two parameter ratio-product-ratio estimator for a finite population mean in a simple random sample without replacement following the methodology in Ray and Sahai (1980), Sahai and Ray (1980), Sahai and Sahai (1985) and Singh and Ruiz Espejo (2003). 
The bias and mean square error of our proposed estimator are obtained to the first degree of approximation. We derive conditions for the parameters under which the proposed estimator has smaller mean square error than the sample mean, ratio and product estimators. 
We carry out an application showing that the proposed estimator outperforms the traditional estimators using groundwater data taken from a geological site in the state of Florida.
]]></description>
<dc:subject>statistics estimation approximation rather-interesting out-of-the-box looking-to-see to-understand consider:looking-to-see consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ddd5fb7c18d8/</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:estimation"/>
	<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:out-of-the-box"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1410.5115">
    <title>[1410.5115] Remarks on the the circumcenter of mass</title>
    <dc:date>2019-08-02T10:56:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1410.5115</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Suppose that to every non-degenerate simplex Delta in n-dimensional Euclidean space a `center' C(Delta) is assigned so that the following assumptions hold: (i) The map that assigns C(Delta) to Delta commutes with similarities and is invariant under the permutations of the vertices of the simplex; (ii) The map that assigns Vol(Delta) C(Delta) to Delta is polynomial in the coordinates of the vertices of the simplex. Then C(Delta) is an affine combination of the center of mass and the circumcenter of Delta (with the coefficients independent of the simplex). The motivation for this theorem comes from the recent study of the circumcenter of mass of simplicial polytopes by the authors and by A. Akopyan.
]]></description>
<dc:subject>plane-geometry construction algorithms feature-construction statistics nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ca56a9c6651c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:plane-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<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://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="https://arxiv.org/abs/1802.07481">
    <title>[1802.07481] Celer: a Fast Solver for the Lasso with Dual Extrapolation</title>
    <dc:date>2019-07-24T10:51:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.07481</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Convex sparsity-inducing regularizations are ubiquitous in high-dimensional machine learning, but solving the resulting optimization problems can be slow. To accelerate solvers, state-of-the-art approaches consist in reducing the size of the optimization problem at hand. In the context of regression, this can be achieved either by discarding irrelevant features (screening techniques) or by prioritizing features likely to be included in the support of the solution (working set techniques). Duality comes into play at several steps in these techniques. Here, we propose an extrapolation technique starting from a sequence of iterates in the dual that leads to the construction of improved dual points. This enables a tighter control of optimality as used in stopping criterion, as well as better screening performance of Gap Safe rules. Finally, we propose a working set strategy based on an aggressive use of Gap Safe screening rules. Thanks to our new dual point construction, we show significant computational speedups on multiple real-world problems.
]]></description>
<dc:subject>machine-learning statistics horse-races performance-measure computational-complexity to-read algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ba797f2dc4e8/</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:horse-races"/>
	<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:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.06038">
    <title>[1812.06038] Inferring the size of the causal universe: features and fusion of causal attribution networks</title>
    <dc:date>2019-06-03T10:47:59+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.06038</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Cause-and-effect reasoning, the attribution of effects to causes, is one of the most powerful and unique skills humans possess. Multiple surveys are mapping out causal attributions as networks, but it is unclear how well these efforts can be combined. Further, the total size of the collective causal attribution network held by humans is currently unknown, making it challenging to assess the progress of these surveys. Here we study three causal attribution networks to determine how well they can be combined into a single network. Combining these networks requires dealing with ambiguous nodes, as nodes represent written descriptions of causes and effects and different descriptions may exist for the same concept. We introduce NetFUSES, a method for combining networks with ambiguous nodes. Crucially, treating the different causal attributions networks as independent samples allows us to use their overlap to estimate the total size of the collective causal attribution network. We find that existing surveys capture 5.77% ± 0.781% of the ≈293 000 causes and effects estimated to exist, and 0.198% ± 0.174% of the ≈10 200 000 attributed cause-effect relationships.]]></description>
<dc:subject>statistics explanation cause-and-effect to-understand looking-to-see network-theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e723fa8c33f7/</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:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cause-and-effect"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1707.05033">
    <title>[1707.05033] Discrete Extremes</title>
    <dc:date>2019-05-04T12:18:05+00:00</dc:date>
    <link>https://arxiv.org/abs/1707.05033</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Our contribution is to widen the scope of extreme value analysis applied to discrete-valued data. Extreme values of a random variable X are commonly modeled using the generalized Pareto distribution, a method that often gives good results in practice. When X is discrete, we propose two other methods using a discrete generalized Pareto and a generalized Zipf distribution respectively. Both are theoretically motivated and we show that they perform well in estimating rare events in several simulated and real data cases such as word frequency, tornado outbreaks and multiple births.
]]></description>
<dc:subject>extreme-values statistics probability-theory 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:22d2214c48ac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t: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/1901.01624">
    <title>[1901.01624] Composite optimization for robust blind deconvolution</title>
    <dc:date>2019-05-03T23:31:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.01624</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The blind deconvolution problem seeks to recover a pair of vectors from a set of rank one bilinear measurements. We consider a natural nonsmooth formulation of the problem and show that under standard statistical assumptions, its moduli of weak convexity, sharpness, and Lipschitz continuity are all dimension independent. This phenomenon persists even when up to half of the measurements are corrupted by noise. Consequently, standard algorithms, such as the subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution. We then complete the paper with a new initialization strategy, complementing the local search algorithms. The initialization procedure is both provably efficient and robust to outlying measurements. Numerical experiments, on both simulated and real data, illustrate the developed theory and methods.
]]></description>
<dc:subject>approximation inverse-problems statistics inference algorithms numerical-methods</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a32e17810786/</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:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1712.07381">
    <title>[1712.07381] Extreme Value Analysis Without the Largest Values: What Can Be Done?</title>
    <dc:date>2019-05-03T11:21:33+00:00</dc:date>
    <link>https://arxiv.org/abs/1712.07381</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we are concerned with the analysis of heavy-tailed data when a portion of the extreme values is unavailable. This research was motivated by an analysis of the degree distributions in a large social network. The degree distributions of such networks tend to have power law behavior in the tails. We focus on the Hill estimator, which plays a starring role in heavy-tailed modeling. The Hill estimator for this data exhibited a smooth and increasing "sample path" as a function of the number of upper order statistics used in constructing the estimator. This behavior became more apparent as we artificially removed more of the upper order statistics. Building on this observation we introduce a new version of the Hill estimator. It is a function of the number of the upper order statistics used in the estimation, but also depends on the number of unavailable extreme values. We establish functional convergence of the normalized Hill estimator to a Gaussian process. An estimation procedure is developed based on the limit theory to estimate the number of missing extremes and extreme value parameters including the tail index and the bias of Hill's estimator. We illustrate how this approach works in both simulations and real data examples.
]]></description>
<dc:subject>statistics extreme-values rather-interesting algorithms estimation inference data-analysis nudge-targets consider:looking-to-see consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a732ab80dda1/</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:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<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:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.02998">
    <title>[1804.02998] Anomaly Detection for Industrial Big Data</title>
    <dc:date>2019-05-02T08:50:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.02998</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[As the Industrial Internet of Things (IIoT) grows, systems are increasingly being monitored by arrays of sensors returning time-series data at ever-increasing 'volume, velocity and variety' (i.e. Industrial Big Data). An obvious use for these data is real-time systems condition monitoring and prognostic time to failure analysis (remaining useful life, RUL). (e.g. See white papers by this http URL, and output of the NASA Prognostics Center of Excellence (PCoE).) However, as noted by Agrawal and Choudhary 'Our ability to collect "big data" has greatly surpassed our capability to analyze it, underscoring the emergence of the fourth paradigm of science, which is data-driven discovery.' In order to fully utilize the potential of Industrial Big Data we need data-driven techniques that operate at scales that process models cannot. Here we present a prototype technique for data-driven anomaly detection to operate at industrial scale. The method generalizes to application with almost any multivariate dataset based on independent ordinations of repeated (bootstrapped) partitions of the dataset and inspection of the joint distribution of ordinal distances.
]]></description>
<dc:subject>anomaly-detection machine-learning dimension-reduction statistics to-write-about algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4fa540317f02/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anomaly-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<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/1709.07662">
    <title>[1709.07662] Estimating the maximum possible earthquake magnitude using extreme value methodology: the Groningen case</title>
    <dc:date>2019-04-27T11:56:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.07662</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The area-characteristic, maximum possible earthquake magnitude TM is required by the earthquake engineering community, disaster management agencies and the insurance industry. The Gutenberg-Richter law predicts that earthquake magnitudes M follow a truncated exponential distribution. In the geophysical literature several estimation procedures were proposed, see for instance Kijko and Singh (Acta Geophys., 2011) and the references therein. Estimation of TM is of course an extreme value problem to which the classical methods for endpoint estimation could be applied. We argue that recent methods on truncated tails at high levels (Beirlant et al., Extremes, 2016; Electron. J. Stat., 2017) constitute a more appropriate setting for this estimation problem. We present upper confidence bounds to quantify uncertainty of the point estimates. We also compare methods from the extreme value and geophysical literature through simulations. Finally, the different methods are applied to the magnitude data for the earthquakes induced by gas extraction in the Groningen province of the Netherlands.
]]></description>
<dc:subject>power-laws geology rather-interesting natural-experiments statistics prediction extreme-values to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f53f76f4e834/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:power-laws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:geology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-experiments"/>
	<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:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nature.com/articles/d41586-019-00857-9">
    <title>Scientists rise up against statistical significance</title>
    <dc:date>2019-04-25T15:12:18+00:00</dc:date>
    <link>https://www.nature.com/articles/d41586-019-00857-9</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Let’s be clear about what must stop: we should never conclude there is ‘no difference’ or ‘no association’ just because a P value is larger than a threshold such as 0.05 or, equivalently, because a confidence interval includes zero. Neither should we conclude that two studies conflict because one had a statistically significant result and the other did not. These errors waste research efforts and misinform policy decisions.

]]></description>
<dc:subject>statistics that-line-right-there-sums-it-up academic-culture publishing pedagogy what-gets-measured-gets-fudged</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a1b50fde778e/</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:that-line-right-there-sums-it-up"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:publishing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pedagogy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:what-gets-measured-gets-fudged"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.06912">
    <title>[1811.06912] Exploring Student Check-In Behavior for Improved Point-of-Interest Prediction</title>
    <dc:date>2019-04-10T10:28:38+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.06912</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[With the availability of vast amounts of user visitation history on location-based social networks (LBSN), the problem of Point-of-Interest (POI) prediction has been extensively studied. However, much of the research has been conducted solely on voluntary checkin datasets collected from social apps such as Foursquare or Yelp. While these data contain rich information about recreational activities (e.g., restaurants, nightlife, and entertainment), information about more prosaic aspects of people's lives is sparse. This not only limits our understanding of users' daily routines, but more importantly the modeling assumptions developed based on characteristics of recreation-based data may not be suitable for richer check-in data. In this work, we present an analysis of education "check-in" data using WiFi access logs collected at Purdue University. We propose a heterogeneous graph-based method to encode the correlations between users, POIs, and activities, and then jointly learn embeddings for the vertices. We evaluate our method compared to previous state-of-the-art POI prediction methods, and show that the assumptions made by previous methods significantly degrade performance on our data with dense(r) activity signals. We also show how our learned embeddings could be used to identify similar students (e.g., for friend suggestions).
]]></description>
<dc:subject>social-dynamics social-networks data-analysis rather-interesting statistics machine-learning clustering data-pageant visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:178a4234fb86/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-pageant"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0188299">
    <title>Second-generation p-values: Improved rigor, reproducibility, &amp; transparency in statistical analyses</title>
    <dc:date>2019-03-29T12:53:38+00:00</dc:date>
    <link>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0188299</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Verifying that a statistically significant result is scientifically meaningful is not only good scientific practice, it is a natural way to control the Type I error rate. Here we introduce a novel extension of the p-value—a second-generation p-value (pδ)–that formally accounts for scientific relevance and leverages this natural Type I Error control. The approach relies on a pre-specified interval null hypothesis that represents the collection of effect sizes that are scientifically uninteresting or are practically null. The second-generation p-value is the proportion of data-supported hypotheses that are also null hypotheses. As such, second-generation p-values indicate when the data are compatible with null hypotheses (pδ = 1), or with alternative hypotheses (pδ = 0), or when the data are inconclusive (0 < pδ < 1). Moreover, second-generation p-values provide a proper scientific adjustment for multiple comparisons and reduce false discovery rates. This is an advance for environments rich in data, where traditional p-value adjustments are needlessly punitive. Second-generation p-values promote transparency, rigor and reproducibility of scientific results by a priori specifying which candidate hypotheses are practically meaningful and by providing a more reliable statistical summary of when the data are compatible with alternative or null hypotheses.

]]></description>
<dc:subject>statistics experimental-design philosophy-of-science define-your-terms performance-measure rather-interesting to-watch prescriptive-advice best-practices academic-culture</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4bf3aaf00953/</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:experimental-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prescriptive-advice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:best-practices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
</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/1711.06588">
    <title>[1711.06588] Dependent landmark drift: robust point set registration with a Gaussian mixture model and a statistical shape model</title>
    <dc:date>2019-02-23T12:03:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.06588</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The goal of point set registration is to find point-by-point correspondences between point sets, each of which characterizes the shape of an object. Because local preservation of object geometry is assumed, prevalent algorithms in the area can often elegantly solve the problems without using geometric information specific to the objects. This means that registration performance can be further improved by using prior knowledge of object geometry. In this paper, we propose a novel point set registration method using the Gaussian mixture model with prior shape information encoded as a statistical shape model. Our transformation model is defined as a combination of the similar transformation, motion coherence, and the statistical shape model. Therefore, the proposed method works effectively if the target point set includes outliers and missing regions, or if it is rotated. The computational cost can be reduced to linear, and therefore the method is scalable to large point sets. The effectiveness of the method will be verified through comparisons with existing algorithms using datasets concerning human body shapes, hands, and faces.]]></description>
<dc:subject>statistics algorithms rather-interesting image-processing optimization to-write-about nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:89cb5bb9b116/</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:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<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:Bag></taxo:topics>
</item>
</rdf:RDF>