<?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 (arsyed)</title>
    <link>https://pinboard.in/u:arsyed/public/</link>
    <description>recent bookmarks from arsyed</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://medium.com/@bhpartee/my-response-to-the-pinker-petition-open-letter-to-the-linguistics-community-80e2e4d9dbe2"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.07780"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2001.05444"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.06342"/>
	<rdf:li rdf:resource="https://science.sciencemag.org/content/366/6461/58"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.12434"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.02214"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.01039"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.01551"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1809.04790"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.00325"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.01670"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.01040"/>
	<rdf:li rdf:resource="https://www.degruyter.com/view/j/jci.2019.7.issue-1/jci-2019-2002/jci-2019-2002.xml"/>
	<rdf:li rdf:resource="https://www.cambridge.org/9781108476676"/>
	<rdf:li rdf:resource="http://proceedings.mlr.press/v80/balestriero18b.html"/>
	<rdf:li rdf:resource="http://www.culturalcognition.net/blog/2018/9/6/return-of-the-chick-sexers.html"/>
	<rdf:li rdf:resource="https://www.nbcnews.com/tech/tech-news/how-three-conspiracy-theorists-took-q-sparked-qanon-n900531"/>
	<rdf:li rdf:resource="https://www.stat.washington.edu/peter/591/labs/Lab4/Lab4.SpatioTemporal.html"/>
	<rdf:li rdf:resource="https://www.sciencedirect.com/science/article/pii/0022249692900356"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007%2FBF00773667?LI=true"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.02774"/>
	<rdf:li rdf:resource="http://talkingpointsmemo.com/edblog/a-serf-on-googles-farm"/>
	<rdf:li rdf:resource="http://crookedtimber.org/2017/08/11/from-a-logical-point-of-view/"/>
	<rdf:li rdf:resource="http://journal.sjdm.org/17/17408/jdm17408.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1601.00013#"/>
	<rdf:li rdf:resource="https://mitpress.mit.edu/books/what-argument"/>
	<rdf:li rdf:resource="http://tuvalu.santafe.edu/~simon/styled-8/"/>
	<rdf:li rdf:resource="http://journals.cambridge.org/action/displayAbstract?fromPage=online&amp;aid=10293503&amp;fileId=S2053447716000099"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1602.04938"/>
	<rdf:li rdf:resource="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-010814-020120"/>
	<rdf:li rdf:resource="http://dx.doi.org/10.1126/science.1229566"/>
	<rdf:li rdf:resource="http://arstechnica.co.uk/security/2016/02/the-nsas-skynet-program-may-be-killing-thousands-of-innocent-people/"/>
	<rdf:li rdf:resource="http://www.tandfonline.com/doi/abs/10.1080/01621459.1979.10481632"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.02284"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.00066"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.05910"/>
	<rdf:li rdf:resource="https://www.youtube.com/channel/UC__8IOjnouIC4rQAoW9xTyA"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.02475"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1504.00494"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1404.1578"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1312.7851"/>
	<rdf:li rdf:resource="http://www.statschat.org.nz/2015/01/20/ask-a-silly-question-get-a-silly-answer/"/>
	<rdf:li rdf:resource="http://lombardi.cs.arizona.edu/"/>
	<rdf:li rdf:resource="http://dl.acm.org/citation.cfm?id=2582139"/>
	<rdf:li rdf:resource="http://press.princeton.edu/titles/10286.html"/>
	<rdf:li rdf:resource="http://www.origamipoems.com/poets/212-garrett-phelan"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/110/37/14837.abstract"/>
	<rdf:li rdf:resource="http://piketty.pse.ens.fr/files/capital21c/en/Piketty2014TechnicalAppendixResponsetoFT.pdf"/>
	<rdf:li rdf:resource="http://mrl.nyu.edu/projects/image-analogies/index.html"/>
	<rdf:li rdf:resource="http://lareviewofbooks.org/essay/85686"/>
	<rdf:li rdf:resource="http://www.jstor.org/stable/270873"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.3808"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.4296"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1101.0673"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/sjos.12075/abstract?systemMessage=Wiley+Online+Library+will+be+disrupted+Saturday%2C+15+March+from+10%3A00-12%3A00+GMT+%2806%3A00-08%3A00+EDT%29+for+essential+maintenance"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1401.1026"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1402.1920"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1402.2499"/>
	<rdf:li rdf:resource="http://www.jstor.org/action/showArticleInfo?doi=10.1086%2F674416"/>
	<rdf:li rdf:resource="http://leighphillips.wordpress.com/2013/05/22/dawkins-vs-democracy/"/>
	<rdf:li rdf:resource="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-022513-115657"/>
	<rdf:li rdf:resource="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-062713-085831"/>
	<rdf:li rdf:resource="http://alyssafrazee.com/introducing-R.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1312.6168"/>
	<rdf:li rdf:resource="http://www.tandfonline.com/doi/abs/10.1080/01621459.2013.847374#.UrhitaXPUlN"/>
	<rdf:li rdf:resource="http://omniorthogonal.blogspot.com/2013/12/endarkenment.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1311.2503"/>
	<rdf:li rdf:resource="http://m.mind.oxfordjournals.org/content/early/2013/10/31/mind.fzt073.full?keytype=ref&amp;ijkey=JaKp6eczj44oA1I"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1310.4210"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://medium.com/@bhpartee/my-response-to-the-pinker-petition-open-letter-to-the-linguistics-community-80e2e4d9dbe2">
    <title>My Response to the Pinker Petition — Open Letter to the Linguistics Community</title>
    <dc:date>2020-07-07T17:00:35+00:00</dc:date>
    <link>https://medium.com/@bhpartee/my-response-to-the-pinker-petition-open-letter-to-the-linguistics-community-80e2e4d9dbe2</link>
    <dc:creator>arsyed</dc:creator><dc:subject>steven-pinker barbara-partee via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:7e609795f778/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:steven-pinker"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:barbara-partee"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.07780">
    <title>[2004.07780] Shortcut Learning in Deep Neural Networks</title>
    <dc:date>2020-04-17T21:52:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.07780</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distil how many of deep learning's problem can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications."]]></description>
<dc:subject>neural-net heuristics shortcut clever-hans via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:08d3aa3f4213/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neural-net"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:shortcut"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:clever-hans"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2001.05444">
    <title>[2001.05444] Spillover Effects in Experimental Data</title>
    <dc:date>2020-03-16T03:04:09+00:00</dc:date>
    <link>https://arxiv.org/abs/2001.05444</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We present current methods for estimating treatment effects and spillover effects under "interference", a term which covers a broad class of situations in which a unit's outcome depends not only on treatments received by that unit, but also on treatments received by other units. To the extent that units react to each other, interact, or otherwise transmit effects of treatments, valid inference requires that we account for such interference, which is a departure from the traditional assumption that units' outcomes are affected only by their own treatment assignment. Interference and associated spillovers may be a nuisance or they may be of substantive interest to the researcher. In this chapter, we focus on interference in the context of randomized experiments. We review methods for when interference happens in a general network setting. We then consider the special case where interference is contained within a hierarchical structure. Finally, we discuss the relationship between interference and contagion. We use the interference R package and simulated data to illustrate key points. We consider efficient designs that allow for estimation of the treatment and spillover effects and discuss recent empirical studies that try to capture such effects."]]></description>
<dc:subject>experiment-design causal-inference via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:257d00d5dc29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:experiment-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causal-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.06342">
    <title>[1909.06342] Explainable Machine Learning in Deployment</title>
    <dc:date>2020-01-09T06:30:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.06342</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactual explanations, or influential training data. Yet there is little understanding of how organizations use these methods in practice. This study explores how organizations view and use explainability for stakeholder consumption. We find that, currently, the majority of deployments are not for end users affected by the model but rather for machine learning engineers, who use explainability to debug the model itself. There is thus a gap between explainability in practice and the goal of transparency, since explanations primarily serve internal stakeholders rather than external ones. Our study synthesizes the limitations of current explainability techniques that hamper their use for end users. To facilitate end user interaction, we develop a framework for establishing clear goals for explainability. We end by discussing concerns raised regarding explainability."]]></description>
<dc:subject>via:rvenkat via:cshalizi machine-learning explanation interpretability</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:2727c62c8fe0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:rvenkat"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:interpretability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://science.sciencemag.org/content/366/6461/58">
    <title>From speech and talkers to the social world: The neural processing of human spoken language | Science</title>
    <dc:date>2019-10-20T20:27:08+00:00</dc:date>
    <link>https://science.sciencemag.org/content/366/6461/58</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Human speech perception is a paradigm example of the complexity of human linguistic processing; however, it is also the dominant way of expressing vocal identity and is critically important for social interactions. Here, I review the ways that the speech, the talker, and the social nature of speech interact and how this may be computed in the human brain, using models and approaches from nonhuman primate studies. I explore the extent to which domain-general approaches may be able to account for some of these neural findings. Finally, I address the importance of extending these findings into a better understanding of the social use of speech in conversations."]]></description>
<dc:subject>speech perception neuroscience psycholinguistics via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:84bbf46c43c9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:speech"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:perception"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:psycholinguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.12434">
    <title>[1909.12434] Learning the Difference that Makes a Difference with Counterfactually-Augmented Data</title>
    <dc:date>2019-10-02T17:03:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.12434</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Despite alarm over the reliance of machine learning systems on so-called spurious patterns in training data, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are those due to a common cause (confounding) vs direct or indirect effects. In this paper, we focus on NLP, introducing methods and resources for training models insensitive to spurious patterns. Given documents and their initial labels, we task humans with revise each document to accord with a counterfactual target label, asking that the revised documents be internally coherent while avoiding any gratuitous changes. Interestingly, on sentiment analysis and natural language inference tasks, classifiers trained on original data fail on their counterfactually-revised counterparts and vice versa. Classifiers trained on combined datasets perform remarkably well, just shy of those specialized to either domain. While classifiers trained on either original or manipulated data alone are sensitive to spurious features (e.g., mentions of genre), models trained on the combined data are insensitive to this signal. We will publicly release both datasets."]]></description>
<dc:subject>data-augmentation counterfactual via:cshalizi causal-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:aa05fcf8902d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:data-augmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:counterfactual"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causal-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1605.02214">
    <title>[1605.02214] On cross-validated Lasso</title>
    <dc:date>2019-08-15T03:02:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.02214</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["In this paper, we derive non-asymptotic error bounds for the Lasso estimator when the penalty parameter for the estimator is chosen using K-fold cross-validation. Our bounds imply that the cross-validated Lasso estimator has nearly optimal rates of convergence in the prediction, L2, and L1 norms. For example, we show that in the model with the Gaussian noise and under fairly general assumptions on the candidate set of values of the penalty parameter, the estimation error of the cross-validated Lasso estimator converges to zero in the prediction norm with the slogp/n‾‾‾‾‾‾‾‾√×log(pn)‾‾‾‾‾‾‾√ rate, where n is the sample size of available data, p is the number of covariates, and s is the number of non-zero coefficients in the model. Thus, the cross-validated Lasso estimator achieves the fastest possible rate of convergence in the prediction norm up to a small logarithmic factor log(pn)‾‾‾‾‾‾‾√, and similar conclusions apply for the convergence rate both in L2 and in L1 norms. Importantly, our results cover the case when p is (potentially much) larger than n and also allow for the case of non-Gaussian noise. Our paper therefore serves as a justification for the widely spread practice of using cross-validation as a method to choose the penalty parameter for the Lasso estimator."]]></description>
<dc:subject>cross-validation lasso regression statistics via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:b133d75663ae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:lasso"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.01039">
    <title>[1908.01039] Linear Dynamics: Clustering without identification</title>
    <dc:date>2019-08-07T02:34:32+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.01039</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Clustering time series is a delicate task; varying lengths and temporal offsets obscure direct comparisons. A natural strategy is to learn a parametric model foreach time series and to cluster the model parameters rather than the sequences themselves. Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical systems is a venerable task, permitting provably efficient solutions only in special cases. In this work, we show that clustering the parameters of unknown linear dynamical systems is, in fact, easier than identifying them. We analyze a computationally efficient clustering algorithm that enjoys provable convergence guarantees under a natural separation assumption. Although easy to implement, our algorithm is general, handling multi-dimensional data with time offsets and partial sequences. Evaluating our algorithm on both synthetic data and real electrocardiogram (ECG) signals, we see significant improvements in clustering quality over existing baselines."]]></description>
<dc:subject>time-series clustering via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:f5eab56c5f88/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.01551">
    <title>[1908.01551] Robust Over-the-Air Adversarial Examples Against Automatic Speech Recognition Systems</title>
    <dc:date>2019-08-07T02:25:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.01551</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Automatic speech recognition (ASR) systems are possible to fool via targeted adversarial examples. These can induce the ASR to produce arbitrary transcriptions in response to any type of audio signal, be it speech, environmental sounds, or music. However, in general, those adversarial examples did not work in a real-world setup, where the examples are played over the air but have to be fed into the ASR system directly. In some cases, where the adversarial examples could be successfully played over the air, the attacks require precise information about the room where the attack takes place in order to tailor the adversarial examples to a specific setup and are not transferable to other rooms. Other attacks, which are robust in an over-the-air attack, are either handcrafted examples or human listeners can easily recognize the target transcription, once they have been alerted to its content. In this paper, we demonstrate the first generic algorithm that produces adversarial examples which remain robust in an over-the-air attack such that the ASR system transcribes the target transcription after actually being replayed. For the proposed algorithm, guessing a rough approximation of the room characteristics is enough and no actual access to the room is required. We use the ASR system Kaldi to demonstrate the attack and employ a room-impulse-response simulator to harden the adversarial examples against varying room characteristics. Further, the algorithm can also utilize psychoacoustics to hide changes of the original audio signal below the human thresholds of hearing. We show that the adversarial examples work for varying room setups, but also can be tailored to specific room setups. As a result, an attacker can optimize adversarial examples for any target transcription and to arbitrary rooms. Additionally, the adversarial examples remain transferable to varying rooms with a high probability."]]></description>
<dc:subject>adversarial-examples via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:b62b30274a46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:adversarial-examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1809.04790">
    <title>[1809.04790] Adversarial Examples: Opportunities and Challenges</title>
    <dc:date>2019-08-07T02:25:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1809.04790</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs) which are designed by attackers to fool deep learning models. Different from real examples, AEs can mislead the model to predict incorrect outputs while hardly be distinguished by human eyes, therefore threaten security-critical deep-learning applications. In recent years, the generation and defense of AEs have become a research hotspot in the field of artificial intelligence (AI) security. This article reviews the latest research progress of AEs. First, we introduce the concept, cause, characteristics and evaluation metrics of AEs, then give a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages. After that, we review the existing defenses and discuss their limitations. Finally, future research opportunities and challenges on AEs are prospected."

]]></description>
<dc:subject>adversarial-examples via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:5e79d8e1dc59/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:adversarial-examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.00325">
    <title>[1908.00325] Estimating the Standard Error of Cross-Validation-Based Estimators of Classification Rules Performance</title>
    <dc:date>2019-08-04T21:06:31+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.00325</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["First, we analyze the variance of the Cross Validation (CV)-based estimators used for estimating the performance of classification rules. Second, we propose a novel estimator to estimate this variance using the Influence Function (IF) approach that had been used previously very successfully to estimate the variance of the bootstrap-based estimators. The motivation for this research is that, as the best of our knowledge, the literature lacks a rigorous method for estimating the variance of the CV-based estimators. What is available is a set of ad-hoc procedures that have no mathematical foundation since they ignore the covariance structure among dependent random variables. The conducted experiments show that the IF proposed method has small RMS error with some bias. However, surprisingly, the ad-hoc methods still work better than the IF-based method. Unfortunately, this is due to the lack of enough smoothness if compared to the bootstrap estimator. This opens the research for three points: (1) more comprehensive simulation study to clarify when the IF method win or loose; (2) more mathematical analysis to figure out why the ad-hoc methods work well; and (3) more mathematical treatment to figure out the connection between the appropriate amount of "smoothness" and decreasing the bias of the IF method."]]></description>
<dc:subject>cross-validation statistics via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:a71b2ca1f7d0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.01670">
    <title>[1907.01670] Double Cross Validation for the Number of Factors in Approximate Factor Models</title>
    <dc:date>2019-07-18T13:41:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.01670</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[ Determining the number of factors is essential to factor analysis. In this paper, we propose {an efficient cross validation (CV)} method to determine the number of factors in approximate factor models. The method applies CV twice, first along the directions of observations and then variables, and hence is referred to hereafter as double cross-validation (DCV). Unlike most CV methods, which are prone to overfitting, the DCV is statistically consistent in determining the number of factors when both dimension of variables and sample size are sufficiently large. Simulation studies show that DCV has outstanding performance in comparison to existing methods in selecting the number of factors, especially when the idiosyncratic error has heteroscedasticity, or heavy tail, or relatively large variance. ]]></description>
<dc:subject>cross-validation model-selection via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:310b09afff17/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.01040">
    <title>[1906.01040] A Surprising Density of Illusionable Natural Speech</title>
    <dc:date>2019-06-06T18:54:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.01040</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[ Recent work on adversarial examples has demonstrated that most natural inputs can be perturbed to fool even state-of-the-art machine learning systems. But does this happen for humans as well? In this work, we investigate: what fraction of natural instances of speech can be turned into "illusions" which either alter humans' perception or result in different people having significantly different perceptions? We first consider the McGurk effect, the phenomenon by which adding a carefully chosen video clip to the audio channel affects the viewer's perception of what is said (McGurk and MacDonald, 1976). We obtain empirical estimates that a significant fraction of both words and sentences occurring in natural speech have some susceptibility to this effect. We also learn models for predicting McGurk illusionability. Finally we demonstrate that the Yanny or Laurel auditory illusion (Pressnitzer et al., 2018) is not an isolated occurrence by generating several very different new instances. We believe that the surprising density of illusionable natural speech warrants further investigation, from the perspectives of both security and cognitive science. Supplementary videos are available at: this https URL. ]]></description>
<dc:subject>speech psychoacoustics adversarial-examples via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:75169b20bcf9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:speech"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:psychoacoustics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:adversarial-examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.degruyter.com/view/j/jci.2019.7.issue-1/jci-2019-2002/jci-2019-2002.xml">
    <title>On the Interpretation of do(x) : Journal of Causal Inference</title>
    <dc:date>2019-05-25T03:20:43+00:00</dc:date>
    <link>https://www.degruyter.com/view/j/jci.2019.7.issue-1/jci-2019-2002/jci-2019-2002.xml</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This paper provides empirical interpretation of the do(x) operator when applied to non-manipulable variables such as race, obesity, or cholesterol level. We view do(x) as an ideal intervention that provides valuable information on the effects of manipulable variables and is thus empirically testable. We draw parallels between this interpretation and ways of enabling machines to learn effects of untried actions from those tried. We end with the conclusion that researchers need not distinguish manipulable from non-manipulable variables; both types are equally eligible to receive the do(x) operator and to produce useful information for decision makers."]]></description>
<dc:subject>causality via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:6bced5b531b4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/9781108476676">
    <title>Time and causality across the sciences</title>
    <dc:date>2019-05-18T07:02:41+00:00</dc:date>
    <link>https://www.cambridge.org/9781108476676</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This book, geared toward academic researchers and graduate students, brings together research on all facets of how time and causality relate across the sciences. Time is fundamental to how we perceive and reason about causes. It lets us immediately rule out the sound of a car crash as its cause. That a cause happens before its effect has been a core, and often unquestioned, part of how we describe causality. Research across disciplines shows that the relationship is much more complex than that. This book explores what that means for both the metaphysics and epistemology of causes - what they are and how we can find them. Across psychology, biology, and the social sciences, common themes emerge, suggesting that time plays a critical role in our understanding. The increasing availability of large time series datasets allows us to ask new questions about causality, necessitating new methods for modeling dynamic systems and incorporating mechanistic information into causal models."]]></description>
<dc:subject>books causality causal-systems time samantha-kleinberg via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:38acfec6ab59/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causal-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:samantha-kleinberg"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://proceedings.mlr.press/v80/balestriero18b.html">
    <title>A Spline Theory of Deep Learning</title>
    <dc:date>2019-05-08T00:31:54+00:00</dc:date>
    <link>http://proceedings.mlr.press/v80/balestriero18b.html</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[ We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of max-affine spline operators (MASOs), which provide a powerful portal through which to view and analyze their inner workings. For instance, conditioned on the input signal, the output of a MASO DN can be written as a simple affine transformation of the input. This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization. Going further, we propose a simple penalty term that can be added to the cost function of any DN learning algorithm to force the templates to be orthogonal with each other; this leads to significantly improved classification performance and reduced overfitting with no change to the DN architecture. The spline partition of the input signal space opens up a new geometric avenue to study how DNs organize signals in a hierarchical fashion. As an application, we develop and validate a new distance metric for signals that quantifies the difference between their partition encodings. ]]></description>
<dc:subject>neural-net splines via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:086fbc3667d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neural-net"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:splines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.culturalcognition.net/blog/2018/9/6/return-of-the-chick-sexers.html">
    <title>cultural cognition project - Cultural Cognition Blog - Return of the chick sexers . . .</title>
    <dc:date>2018-09-10T02:45:10+00:00</dc:date>
    <link>http://www.culturalcognition.net/blog/2018/9/6/return-of-the-chick-sexers.html</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["That anxiety that judges will disagree based on their “ideologies” bothers me not a bit.

What does bother me—more than just a bit—is the prospect that the men and women I’m training to be lawyers and judges will, despite the diversity of their political and moral sensibilities, converge on outcomes that defy the basic liberal principles that we expect to animate our institutions.

The only thing that I can hope will stop that from happening is for me to tell them that this is how it works.  Because if it troubles me, I have every reason to think that they, as reflective decent people committed to respecting the freedom & reason of others, will find some of this troubling too.

Not so troubling that they can’t become good lawyers. 

But maybe troubling enough that they won't stop being reflective moral people in their careers as lawyers; troubling enough so that if they find themselves in a position to do so, they will enrich the stock of virtuous-lawyer prototypes that populate our situation sense  by doing something  that they, as reflective, moral people—“conservative” or “liberal”—recognize is essential to reconciling being a “good lawyer” with being a member of a profession essential to the good of a liberal democratic regime."]]></description>
<dc:subject>ideology expertise reasoning via:cshalizi law</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:357817caf2a0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:ideology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:expertise"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:reasoning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:law"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nbcnews.com/tech/tech-news/how-three-conspiracy-theorists-took-q-sparked-qanon-n900531">
    <title>How three conspiracy theorists took 'Q' and sparked Qanon</title>
    <dc:date>2018-08-15T18:22:29+00:00</dc:date>
    <link>https://www.nbcnews.com/tech/tech-news/how-three-conspiracy-theorists-took-q-sparked-qanon-n900531</link>
    <dc:creator>arsyed</dc:creator><dc:subject>conspiracy politics via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:54e1771cc640/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:conspiracy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.stat.washington.edu/peter/591/labs/Lab4/Lab4.SpatioTemporal.html">
    <title>Modeling using the SpatioTemporal R package</title>
    <dc:date>2018-08-08T02:26:23+00:00</dc:date>
    <link>https://www.stat.washington.edu/peter/591/labs/Lab4/Lab4.SpatioTemporal.html</link>
    <dc:creator>arsyed</dc:creator><dc:subject>R libs spatiotemporal via:cshalizi via:csantos</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:295c427c6a57/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:R"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:libs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:spatiotemporal"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:csantos"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.sciencedirect.com/science/article/pii/0022249692900356">
    <title>Norbert Wiener on the theory of measurement 1914 1915 1921 - ScienceDirect</title>
    <dc:date>2018-02-26T20:28:40+00:00</dc:date>
    <link>https://www.sciencedirect.com/science/article/pii/0022249692900356</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["These words, written by Norbert Wiener in 1919 when he was 24 years old, appear near the end of the third of three extraordinary papers on the theory of relations and measurement that he began before his twentieth birthday. The papers use the notation of Principia Mathematica, which is fairly inaccessible to modern readers. However, Wiener's contributions to measurement theory deserve to be remembered because they include important concepts that were rediscovered by others and now have a central place in the representational theory of measurement and in graph theory. Our purpose is to recount in modern terms Wiener's work in these areas."]]></description>
<dc:subject>measurement norbert-wiener via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:d9049a0cfa74/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:measurement"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:norbert-wiener"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007%2FBF00773667?LI=true">
    <title>Model selection and prediction: Normal regression | SpringerLink</title>
    <dc:date>2018-01-24T23:30:57+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007%2FBF00773667?LI=true</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This paper discusses the topic of model selection for finite-dimensional normal regression models. We compare model selection criteria according to prediction errors based upon prediction with refitting, and prediction without refitting. We provide a new lower bound for prediction without refitting, while a lower bound for prediction with refitting was given by Rissanen. Moreover, we specify a set of sufficient conditions for a model selection criterion to achieve these bounds. Then the achievability of the two bounds by the following selection rules are addressed: Rissanen's accumulated prediction error criterion (APE), his stochastic complexity criterion, AIC, BIC and the FPE criteria. In particular, we provide upper bounds on overfitting and underfitting probabilities needed for the achievability. Finally, we offer a brief discussion on the issue of finite-dimensional vs. infinite-dimensional model assumptions.']]></description>
<dc:subject>papers statistics regression model-selection via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:00142aa9b829/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.02774">
    <title>[1801.02774] Adversarial Spheres</title>
    <dc:date>2018-01-24T04:59:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.02774</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["State of the art computer vision models have been shown to be vulnerable to small adversarial perturbations of the input. In other words, most images in the data distribution are both correctly classified by the model and are very close to a visually similar misclassified image. Despite substantial research interest, the cause of the phenomenon is still poorly understood and remains unsolved. We hypothesize that this counter intuitive behavior is a naturally occurring result of the high dimensional geometry of the data manifold. As a first step towards exploring this hypothesis, we study a simple synthetic dataset of classifying between two concentric high dimensional spheres. For this dataset we show a fundamental tradeoff between the amount of test error and the average distance to nearest error. In particular, we prove that any model which misclassifies a small constant fraction of a sphere will be vulnerable to adversarial perturbations of size O(1/d‾‾√). Surprisingly, when we train several different architectures on this dataset, all of their error sets naturally approach this theoretical bound. As a result of the theory, the vulnerability of neural networks to small adversarial perturbations is a logical consequence of the amount of test error observed. We hope that our theoretical analysis of this very simple case will point the way forward to explore how the geometry of complex real-world data sets leads to adversarial examples."]]></description>
<dc:subject>papers adversarial-examples classification via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:69300443fa5b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:adversarial-examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://talkingpointsmemo.com/edblog/a-serf-on-googles-farm">
    <title>A Serf on Google’s Farm – Talking Points Memo</title>
    <dc:date>2017-09-01T15:17:34+00:00</dc:date>
    <link>http://talkingpointsmemo.com/edblog/a-serf-on-googles-farm</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Now, certainly you’re figuring we could contact someone at Google at explain that we’re not publishing hate speech and racist violence. We’re reporting on it. Not really. We tried that. We got back a message from our rep not really understanding the distinction and cheerily telling us to try to operate within the no hate speech rules. And how many warnings until we’re blacklisted? Who knows?"]]></description>
<dc:subject>google media tpm journalism monopoly via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:01194c208ddd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:media"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:tpm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:journalism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:monopoly"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://crookedtimber.org/2017/08/11/from-a-logical-point-of-view/">
    <title>From a logical point of view … — Crooked Timber</title>
    <dc:date>2017-08-13T23:44:04+00:00</dc:date>
    <link>http://crookedtimber.org/2017/08/11/from-a-logical-point-of-view/</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["But what really struck me was that I have changed in my old age; I used to be depressed at the generally very poor level of statistical education, now I’m depressed at the extent to which people with an excellent education in statistics still don’t really understand anything about the subject. I’m beginning to think that mathematical training in many cases is actually damaging; simple and robust metrics, usually drawn from the early days of industrial quality control, are what people need to understand.

The true underlying distributions would be useful if Google’s hiring process was to select people at random from the population, put them through a standard test of the single “quality” variable of interest, then take the ones who passed the test and discard the ones who failed.  [...]

The male/female ratio at Google is not the outcome of a neutral process; it’s a variable under Google’s control. And when you think of the male/female ratio as an input rather than an output, you can start thinking about recruitment as a quality control process and everything becomes much simpler."]]></description>
<dc:subject>gender tech statistics via:vaguery via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:a6e12a938384/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:gender"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:tech"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:vaguery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://journal.sjdm.org/17/17408/jdm17408.html">
    <title>How generalizable is good judgment? A multi-task, multi-benchmark study</title>
    <dc:date>2017-08-03T05:13:33+00:00</dc:date>
    <link>http://journal.sjdm.org/17/17408/jdm17408.html</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Good judgment is often gauged against two gold standards – coherence and correspondence. Judgments are coherent if they demonstrate consistency with the axioms of probability theory or propositional logic. Judgments are correspondent if they agree with ground truth. When gold standards are unavailable, silver standards such as consistency and discrimination can be used to evaluate judgment quality. Individuals are consistent if they assign similar judgments to comparable stimuli, and they discriminate if they assign different judgments to dissimilar stimuli. We ask whether “superforecasters”, individuals with noteworthy correspondence skills (see Mellers et al., 2014) show superior performance on laboratory tasks assessing other standards of good judgment. Results showed that superforecasters either tied or out-performed less correspondent forecasters and undergraduates with no forecasting experience on tests of consistency, discrimination, and coherence. While multifaceted, good judgment may be a more unified than concept than previously thought."]]></description>
<dc:subject>papers decision psychology judgement philip-tetlock via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:9d5ee3b1714b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:decision"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:judgement"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:philip-tetlock"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1601.00013#">
    <title>[1601.00013] A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function</title>
    <dc:date>2016-07-04T15:04:07+00:00</dc:date>
    <link>http://arxiv.org/abs/1601.00013#</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can approximate an arbitrary continuous function provided that an unlimited number of neurons in a hidden layer is permitted. In this paper, we consider constructive approximation on any finite interval of ℝ by neural networks with only one neuron in the hidden layer. We construct algorithmically a smooth, sigmoidal, almost monotone activation function σ providing approximation to an arbitrary continuous function within any degree of accuracy. This algorithm is implemented in a computer program, which computes the value of σ at any reasonable point of the real axis."]]></description>
<dc:subject>papers neural-net approximation via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:a7759cb4fc29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neural-net"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://mitpress.mit.edu/books/what-argument">
    <title>What Is the Argument? | The MIT Press</title>
    <dc:date>2016-06-08T20:39:08+00:00</dc:date>
    <link>https://mitpress.mit.edu/books/what-argument</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["The best way to introduce students to philosophy and philosophical discourse is to have them read and wrestle with original sources. This textbook explores philosophy through detailed argument analyses of texts by philosophers from Plato to Strawson. It presents a novel and transparent method of analysis that will teach students not only how to understand and evaluate philosophers' arguments but also how to construct such arguments themselves. Students will learn to read a text and discover what the philosopher thinks, why the philosopher thinks it, and whether the supporting argument is good.

Students learn argument analysis through argument diagrams, with color-coding of the argument's various elements—conclusion, claims, and “indicator phrases.” (An online “mini-course” in argument diagramming and argument diagramming software are both freely available online.) Each chapter ends with exercises and reading questions. "]]></description>
<dc:subject>books philosophy critical-thinking rhetoric argument argumentation via:cshalizi .dl</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:e6a4da006259/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:critical-thinking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:rhetoric"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:argument"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:argumentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.dl"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://tuvalu.santafe.edu/~simon/styled-8/">
    <title>SFIHMM (Estimating Hidden Markov Models)</title>
    <dc:date>2016-06-08T20:35:59+00:00</dc:date>
    <link>http://tuvalu.santafe.edu/~simon/styled-8/</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["high-speed C code for the estimation of Hidden Markov Models (finite state machines) on arbitrary time-series, for Viterbi Path Reconstruction, and for the generation of simulated data from HMMs. Based on the code used in “Conflict and Computation on Wikipedia: a Finite-State Machine Analysis of Editor Interactions”.]]></description>
<dc:subject>c libs hmm via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:55302c1b8f0b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:c"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:libs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hmm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://journals.cambridge.org/action/displayAbstract?fromPage=online&amp;aid=10293503&amp;fileId=S2053447716000099">
    <title>[Aristotle], &lt;i&gt;On Trolling&lt;/i&gt; - Cambridge Journals Online</title>
    <dc:date>2016-05-09T00:50:56+00:00</dc:date>
    <link>http://journals.cambridge.org/action/displayAbstract?fromPage=online&amp;aid=10293503&amp;fileId=S2053447716000099</link>
    <dc:creator>arsyed</dc:creator><dc:subject>trolling via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:36734be8dde2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:trolling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1602.04938">
    <title>[1602.04938] &quot;Why Should I Trust You?&quot;: Explaining the Predictions of Any Classifier</title>
    <dc:date>2016-03-23T01:54:01+00:00</dc:date>
    <link>http://arxiv.org/abs/1602.04938</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust in a model. Trust is fundamental if one plans to take action based on a prediction, or when choosing whether or not to deploy a new model. Such understanding further provides insights into the model, which can be used to turn an untrustworthy model or prediction into a trustworthy one.
In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction. We further propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). The usefulness of explanations is shown via novel experiments, both simulated and with human subjects. Our explanations empower users in various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and detecting why a classifier should not be trusted. ]]></description>
<dc:subject>via:cshalizi explanation via:rvenkat papers machine-learning interpretability</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:a863853e4785/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:explanation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:rvenkat"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:interpretability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-010814-020120">
    <title>Learning Deep Generative Models - Annual Review of Statistics and Its Application, 2(1):361</title>
    <dc:date>2016-03-23T01:52:45+00:00</dc:date>
    <link>http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-010814-020120</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many artificial intelligence–related tasks, including object recognition, speech perception, and language understanding. Theoretical and biological arguments strongly suggest that building such systems requires models with deep architectures that involve many layers of nonlinear processing. In this article, we review several popular deep learning models, including deep belief networks and deep Boltzmann machines. We show that (a) these deep generative models, which contain many layers of latent variables and millions of parameters, can be learned efficiently, and (b) the learned high-level feature representations can be successfully applied in many application domains, including visual object recognition, information retrieval, classification, and regression tasks.]]></description>
<dc:subject>via:cshalizi papers surveys deep-learning neural-net generative .dl generative-models</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:bcf906d8ff28/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:surveys"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neural-net"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:generative"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.dl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:generative-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://dx.doi.org/10.1126/science.1229566">
    <title>Identifying Personal Genomes by Surname Inference | Science</title>
    <dc:date>2016-03-16T19:05:25+00:00</dc:date>
    <link>http://dx.doi.org/10.1126/science.1229566</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Sharing sequencing data sets without identifiers has become a common practice in genomics. Here, we report that surnames can be recovered from personal genomes by profiling short tandem repeats on the Y chromosome (Y-STRs) and querying recreational genetic genealogy databases. We show that a combination of a surname with other types of metadata, such as age and state, can be used to triangulate the identity of the target. A key feature of this technique is that it entirely relies on free, publicly accessible Internet resources. We quantitatively analyze the probability of identification for U.S. males. We further demonstrate the feasibility of this technique by tracing back with high probability the identities of multiple participants in public sequencing projects."]]></description>
<dc:subject>privacy genetics statistics via:arthegall genomics via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:c9a905bd4e52/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:genomics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arstechnica.co.uk/security/2016/02/the-nsas-skynet-program-may-be-killing-thousands-of-innocent-people/">
    <title>The NSA’s SKYNET program may be killing thousands of innocent people | Ars Technica UK</title>
    <dc:date>2016-02-17T02:27:04+00:00</dc:date>
    <link>http://arstechnica.co.uk/security/2016/02/the-nsas-skynet-program-may-be-killing-thousands-of-innocent-people/</link>
    <dc:creator>arsyed</dc:creator><dc:subject>nsa surveillance warfare drone machine-learning via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:fe2ff200e8ae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:nsa"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:surveillance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:warfare"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:drone"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tandfonline.com/doi/abs/10.1080/01621459.1979.10481632">
    <title>A Predictive Approach to Model Selection - Journal of the American Statistical Association - Volume 74, Issue 365</title>
    <dc:date>2015-11-08T21:52:57+00:00</dc:date>
    <link>http://www.tandfonline.com/doi/abs/10.1080/01621459.1979.10481632</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This article offers a synthesis of Bayesian and sample-reuse approaches to the problem of high structure model selection geared to prediction. Similar methods are used for low structure models. Nested and nonnested paradigms are discussed and examples given."
]]></description>
<dc:subject>papers statistics bayesian prediction model-selection cross-validation via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:256b2cb6d735/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:bayesian"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.02284">
    <title>[1507.02284] The Information Sieve</title>
    <dc:date>2015-08-06T03:04:15+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.02284</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We introduce a new framework for unsupervised learning of deep representations based on a novel hierarchical decomposition of information. Intuitively, data is passed through a series of progressively fine-grained sieves. Each layer of the sieve recovers a single latent factor that is maximally informative about multivariate dependence in the data. The data is transformed after each pass so that the remaining unexplained information trickles down to the next layer. Ultimately, we are left with a set of latent factors explaining all the dependence in the original data and remainder information consisting of independent noise. We present a practical implementation of this framework for discrete variables and apply it to a variety of tasks including independent component analysis, lossy and lossless compression, and predicting missing values in data."]]></description>
<dc:subject>via:cshalizi papers machine-learning information-theory representation-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:875c3e28ecf3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:representation-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.00066">
    <title>[1507.00066] Fast Cross-Validation for Incremental Learning</title>
    <dc:date>2015-08-06T03:03:16+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.00066</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Cross-validation (CV) is one of the main tools for performance estimation and parameter tuning in machine learning. The general recipe for computing CV estimate is to run a learning algorithm separately for each CV fold, a computationally expensive process. In this paper, we propose a new approach to reduce the computational burden of CV-based performance estimation. As opposed to all previous attempts, which are specific to a particular learning model or problem domain, we propose a general method applicable to a large class of incremental learning algorithms, which are uniquely fitted to big data problems. In particular, our method applies to a wide range of supervised and unsupervised learning tasks with different performance criteria, as long as the base learning algorithm is incremental. We show that the running time of the algorithm scales logarithmically, rather than linearly, in the number of CV folds. Furthermore, the algorithm has favorable properties for parallel and distributed implementation. Experiments with state-of-the-art incremental learning algorithms confirm the practicality of the proposed method."]]></description>
<dc:subject>cross-validation via:cshalizi papers</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:bfcc8eab5f95/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.05910">
    <title>[1507.05910] Clustering is Efficient for Approximate Maximum Inner Product Search</title>
    <dc:date>2015-08-06T03:02:45+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.05910</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Locality Sensitive Hashing (LSH) techniques have recently become a popular solution for solving the approximate Maximum Inner Product Search (MIPS) problem, which arises in many situations and have in particular been used as a speed-up for the training of large neural probabilistic language models. 
"In this paper we propose a new approach for solving approximate MIPS based on a variant of the k-means algorithm. We suggest using spherical k-means which is an algorithm that can efficiently be used to solve the approximate Maximum Cosine Similarity Search (MCSS), and basing ourselves on previous work by Shrivastava and Li we show how it can be adapted for approximate MIPS. 
"Our new method compares favorably with LSH-based methods on a simple recall rate test, by providing a more accurate set of candidates for the maximum inner product. The proposed method is thus likely to benefit the wide range of problems with very large search spaces where a robust approximate MIPS heuristic could be of interest, such as for providing a high quality short list of candidate words to speed up the training of neural probabilistic language models."]]></description>
<dc:subject>hashing clustering k-means via:cshalizi database lsh</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:71b78492cc8f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hashing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:k-means"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:lsh"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/channel/UC__8IOjnouIC4rQAoW9xTyA">
    <title>The DeLorean Sisters - YouTube</title>
    <dc:date>2015-07-09T20:44:32+00:00</dc:date>
    <link>https://www.youtube.com/channel/UC__8IOjnouIC4rQAoW9xTyA</link>
    <dc:creator>arsyed</dc:creator><dc:subject>bands music retro nostalgia via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:f5344aa4797d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:bands"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:music"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:retro"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:nostalgia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.02475">
    <title>[1505.02475] Foundational principles for large scale inference: Illustrations through correlation mining</title>
    <dc:date>2015-05-21T09:08:19+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.02475</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["When can reliable inference be drawn in the "Big Data" context? This paper presents a framework for answering this fundamental question in the context of correlation mining, with implications for general large scale inference. In large scale data applications like genomics, connectomics, and eco-informatics the dataset is often variable-rich but sample-starved: a regime where the number n of acquired samples (statistical replicates) is far fewer than the number p of observed variables (genes, neurons, voxels, or chemical constituents). Much of recent work has focused on understanding the computational complexity of proposed methods for "Big Data." Sample complexity however has received relatively less attention, especially in the setting when the sample size n is fixed, and the dimension p grows without bound. To address this gap, we develop a unified statistical framework that explicitly quantifies the sample complexity of various inferential tasks. Sampling regimes can be divided into several categories: 1) the classical asymptotic regime where the variable dimension is fixed and the sample size goes to infinity; 2) the mixed asymptotic regime where both variable dimension and sample size go to infinity at comparable rates; 3) the purely high dimensional asymptotic regime where the variable dimension goes to infinity and the sample size is fixed. Each regime has its niche but only the latter regime applies to exa-scale data dimension. We illustrate this high dimensional framework for the problem of correlation mining, where it is the matrix of pairwise and partial correlations among the variables that are of interest. We demonstrate various regimes of correlation mining based on the unifying perspective of high dimensional learning rates and sample complexity for different structured covariance models and different inference tasks."]]></description>
<dc:subject>statistics via:cshalizi papers correlation-mining highdim</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:9768388271da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:correlation-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:highdim"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1504.00494">
    <title>[1504.00494] Minimal class of models for high-dimensional data</title>
    <dc:date>2015-05-21T09:07:47+00:00</dc:date>
    <link>http://arxiv.org/abs/1504.00494</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Model selection consistency in the high-dimensional regression setting can be achieved only if strong assumptions are fulfilled. We therefore suggest to pursue a different goal, which we call class of minimal models. The class of minimal models includes models that are similar in their prediction accuracy but not necessarily in their elements. We suggest a random search algorithm to reveal candidate models. The algorithm implements simulated annealing while using a score for each predictor that we suggest to derive using a combination of the Lasso and the Elastic Net. The utility of using a class of minimal models is demonstrated in the analysis of two datasets."]]></description>
<dc:subject>statistics misspecification via:cshalizi papers highdim model-selection</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:882c98ddca95/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:misspecification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:highdim"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1404.1578">
    <title>[1404.1578] Models as Approximations: How Random Predictors and Model Violations Invalidate Classical Inference in Regression</title>
    <dc:date>2015-02-01T18:23:01+00:00</dc:date>
    <link>http://arxiv.org/abs/1404.1578</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We review and interpret the early insights of Halbert White who over thirty years ago inaugurated a form of statistical inference for regression models that is asymptotically correct even under "model misspecification," that is, under the assumption that models are approximations rather than generative truths. This form of inference, which is pervasive in econometrics, relies on the "sandwich estimator" of standard error. Whereas linear models theory in statistics assumes models to be true and predictors to be fixed, White's theory permits models to be approximate and predictors to be random. Careful reading of his work shows that the deepest consequences for statistical inference arise from a synergy --- a "conspiracy" --- of nonlinearity and randomness of the predictors which invalidates the ancillarity argument that justifies conditioning on the predictors when they are random. Unlike the standard error of linear models theory, the sandwich estimator provides asymptotically correct inference in the presence of both nonlinearity and heteroskedasticity. An asymptotic comparison of the two types of standard error shows that discrepancies between them can be of arbitrary magnitude. If there exist discrepancies, standard errors from linear models theory are usually too liberal even though occasionally they can be too conservative as well. A valid alternative to the sandwich estimator is provided by the "pairs bootstrap"; in fact, the sandwich estimator can be shown to be a limiting case of the pairs bootstrap. We conclude by giving meaning to regression slopes when the linear model is an approximation rather than a truth. --- In this review we limit ourselves to linear least squares regression, but many qualitative insights hold for most forms of regression."]]></description>
<dc:subject>statistics regression bootstrap misspecification estimation approximation via:cshalizi papers linear-regression</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:3502ade8b90c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:misspecification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:linear-regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1312.7851">
    <title>[1312.7851] Effective Degrees of Freedom: A Flawed Metaphor</title>
    <dc:date>2015-01-25T18:31:39+00:00</dc:date>
    <link>http://arxiv.org/abs/1312.7851</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["To most applied statisticians, a fitting procedure's degrees of freedom is synonymous with its model complexity, or its capacity for overfitting to data. In particular, it is often used to parameterize the bias-variance tradeoff in model selection. We argue that, contrary to folk intuition, model complexity and degrees of freedom are not synonymous and may correspond very poorly. We exhibit and theoretically explore various examples of fitting procedures for which degrees of freedom is not monotonic in the model complexity parameter, and can exceed the total dimension of the response space. Even in very simple settings, the degrees of freedom can exceed the dimension of the ambient space by an arbitrarily large amount. We show the degrees of freedom for any non-convex projection method can be unbounded."]]></description>
<dc:subject>papers statistics model-selection degrees-of-freedom via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:a995cbb69617/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:degrees-of-freedom"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.statschat.org.nz/2015/01/20/ask-a-silly-question-get-a-silly-answer/">
    <title>Ask a silly question, get a silly answer | Stats Chat</title>
    <dc:date>2015-01-22T04:43:33+00:00</dc:date>
    <link>http://www.statschat.org.nz/2015/01/20/ask-a-silly-question-get-a-silly-answer/</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["If you ask a question that is nuts when interpreted precisely, but is basically similar to a sensible question, people are going to answer the question they think you meant to ask. People are helpful that way, even when it isn’t helpful."]]></description>
<dc:subject>surveys bad-data-analysis via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:a0fdd324c6db/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:surveys"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:bad-data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lombardi.cs.arizona.edu/">
    <title>Lombardi Spring Embedder</title>
    <dc:date>2014-11-19T16:33:39+00:00</dc:date>
    <link>http://lombardi.cs.arizona.edu/</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Presented here is a new method of graph visualization, inspired by the style of the American artist Mark Lombardi. This method has two characteristics that differ from regular graph drawings: straight edges are replaced by circular arcs and the arcs around a vertex are evenly spaced out."]]></description>
<dc:subject>algorithms visualization graph graph-drawing layout mark-lombardi via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:ceeb36aff621/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:graph-drawing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:layout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:mark-lombardi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://dl.acm.org/citation.cfm?id=2582139">
    <title>Metric Embedding, Hyperbolic Space, and Social Networks</title>
    <dc:date>2014-10-15T10:23:30+00:00</dc:date>
    <link>http://dl.acm.org/citation.cfm?id=2582139</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We consider the problem of embedding an undirected graph into hyperbolic space with minimum distortion. A fundamental problem in its own right, it has also drawn a great deal of interest from applied communities interested in empirical analysis of large-scale graphs. In this paper, we establish a connection between distortion and quasi-cyclicity of graphs, and use it to derive lower and upper bounds on metric distortion. Two particularly simple and natural graphs with large quasi-cyclicity are n-node cycles and n × n square lattices, and our lower bound shows that any hyperbolic-space embedding of these graphs incurs a multiplicative distortion of at least Ω(n/log n). This is in sharp contrast to Euclidean space, where both of these graphs can be embedded with only constant multiplicative distortion. We also establish a relation between quasi-cyclicity and δ-hyperbolicity of a graph as a way to prove upper bounds on the distortion. Using this relation, we show that graphs with small quasi-cyclicity can be embedded into hyperbolic space with only constant additive distortion. Finally, we also present an efficient (linear-time) randomized algorithm for embedding a graph with small quasi-cyclicity into hyperbolic space, so that with high probability at least a (1 − &epsis;) fraction of the node-pairs has only constant additive distortion. Our results also give a plausible theoretical explanation for why social networks have been observed to embed well into hyperbolic space: they tend to have small quasi-cyclicity."]]></description>
<dc:subject>geometry via:cshalizi hyperbolic-geometry networks embedding papers</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:afd4d27ac744/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hyperbolic-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:embedding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://press.princeton.edu/titles/10286.html">
    <title>Vidyasagar, M.: Hidden Markov Processes: Theory and Applications to Biology</title>
    <dc:date>2014-10-15T10:21:32+00:00</dc:date>
    <link>http://press.princeton.edu/titles/10286.html</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This book explores important aspects of Markov and hidden Markov processes and the applications of these ideas to various problems in computational biology. The book starts from first principles, so that no previous knowledge of probability is necessary. However, the work is rigorous and mathematical, making it useful to engineers and mathematicians, even those not interested in biological applications. A range of exercises is provided, including drills to familiarize the reader with concepts and more advanced problems that require deep thinking about the theory. Biological applications are taken from post-genomic biology, especially genomics and proteomics.
"The topics examined include standard material such as the Perron-Frobenius theorem, transient and recurrent states, hitting probabilities and hitting times, maximum likelihood estimation, the Viterbi algorithm, and the Baum-Welch algorithm. The book contains discussions of extremely useful topics not usually seen at the basic level, such as ergodicity of Markov processes, Markov Chain Monte Carlo (MCMC), information theory, and large deviation theory for both i.i.d and Markov processes. The book also presents state-of-the-art realization theory for hidden Markov models. Among biological applications, it offers an in-depth look at the BLAST (Basic Local Alignment Search Technique) algorithm, including a comprehensive explanation of the underlying theory. Other applications such as profile hidden Markov models are also explored."]]></description>
<dc:subject>genomics bioinformatics via:cshalizi books hmm</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:5d980304def1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:genomics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hmm"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.origamipoems.com/poets/212-garrett-phelan">
    <title>Origami poems: Garrett Phelan</title>
    <dc:date>2014-06-23T01:06:54+00:00</dc:date>
    <link>http://www.origamipoems.com/poets/212-garrett-phelan</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["My high school English teacher's poetry.  (Garrett taught me more about how to write than anyone else, so if you like what you read on my site...)" [cshalizi]]]></description>
<dc:subject>poetry via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:d7d42395b48d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:poetry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/110/37/14837.abstract">
    <title>Beliefs about willpower determine the impact of glucose on self-control</title>
    <dc:date>2014-06-18T16:59:42+00:00</dc:date>
    <link>http://www.pnas.org/content/110/37/14837.abstract</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Past research found that the ingestion of glucose can enhance self-control. It has been widely assumed that basic physiological processes underlie this effect. We hypothesized that the effect of glucose also depends on people’s theories about willpower. Three experiments, both measuring (experiment 1) and manipulating (experiments 2 and 3) theories about willpower, showed that, following a demanding task, only people who view willpower as limited and easily depleted (a limited resource theory) exhibited improved self-control after sugar consumption. In contrast, people who view willpower as plentiful (a nonlimited resource theory) showed no benefits from glucose—they exhibited high levels of self-control performance with or without sugar boosts. Additionally, creating beliefs about glucose ingestion (experiment 3) did not have the same effect as ingesting glucose for those with a limited resource theory. We suggest that the belief that willpower is limited sensitizes people to cues about their available resources including physiological cues, making them dependent on glucose boosts for high self-control performance."
 
cshalizi: "--- Contributed rather than peer-reviewed, so who knows?"]]></description>
<dc:subject>papers psychology will-power glucose via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:8dcb4f775b6c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:will-power"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:glucose"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://piketty.pse.ens.fr/files/capital21c/en/Piketty2014TechnicalAppendixResponsetoFT.pdf">
    <title>Response to FT</title>
    <dc:date>2014-06-05T02:41:38+00:00</dc:date>
    <link>http://piketty.pse.ens.fr/files/capital21c/en/Piketty2014TechnicalAppendixResponsetoFT.pdf</link>
    <dc:creator>arsyed</dc:creator><dc:subject>economics inequality thomas-piketty via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:842e115e3cb4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:thomas-piketty"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mrl.nyu.edu/projects/image-analogies/index.html">
    <title>NYU Media Research Lab | Projects | Image Analogies</title>
    <dc:date>2014-04-28T14:55:26+00:00</dc:date>
    <link>http://mrl.nyu.edu/projects/image-analogies/index.html</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We present a new framework for processing images by example, called "image analogies." Rather than attempting to program individual filters by hand, we attempt to automatically learn filters from training data. For example, the following figure demonstrates an image analogy used to learn a painting style:

The images on the left are training data; our system "learns" the transformation from A to A', and then applies that transformation to B to get B'. In other words, we compute B' to complete the analogy. (Only partial images are shown above; here are the full images)."]]></description>
<dc:subject>machine-learning analogy filters via:cshalizi papers image-processing similarity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:c24e04cbd46c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:analogy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:filters"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:similarity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lareviewofbooks.org/essay/85686">
    <title>Kyrgyzstan and the Uzbeks by Max de Haldevang</title>
    <dc:date>2014-04-18T13:33:35+00:00</dc:date>
    <link>http://lareviewofbooks.org/essay/85686</link>
    <dc:creator>arsyed</dc:creator><dc:subject>kyrgyzstan uzbeks central-asia via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:ca36f726a7d8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:kyrgyzstan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:uzbeks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:central-asia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/stable/270873">
    <title>The Algebra of Blockmodeling</title>
    <dc:date>2014-03-28T01:54:49+00:00</dc:date>
    <link>http://www.jstor.org/stable/270873</link>
    <dc:creator>arsyed</dc:creator><dc:subject>papers networks clustering community-discovery blockmodels algebra via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:10aaf80296e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:community-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:blockmodels"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:algebra"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.3808">
    <title>[1403.3808] Detecting Gradual Changes in Locally Stationary Processes</title>
    <dc:date>2014-03-22T23:11:44+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.3808</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA[In a wide range of applications, the stochastic properties of the observed time series change over time. The changes often occur gradually rather than abruptly: the prop- erties are (approximately) constant for some time and then slowly start to change. In such situations, it is frequently of interest to locate the time point where the properties start to vary. In contrast to the analysis of abrupt changes, methods for detecting smooth or gradual change points are less developed and often require strong paramet- ric assumptions. In this paper, we develop a fully nonparametric method to estimate a smooth change point in a locally stationary framework. We set up a general procedure which allows to deal with a wide variety of stochastic properties including the mean, (auto)covariances and higher-order moments. The theoretical part of the paper estab- lishes the convergence rate of the new estimator. In addition, we examine its finite sample performance by means of a simulation study and illustrate the methodology by applications to temperature and financial return data.
]]></description>
<dc:subject>papers statistics time-series non-stationarity changepoint via:cshalizi .se .print</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:ba06046e96f2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:non-stationarity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:changepoint"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.se"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.print"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.4296">
    <title>[1403.4296] Inference for feature selection using the Lasso with high-dimensional data</title>
    <dc:date>2014-03-22T23:07:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.4296</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Penalized regression models such as the Lasso have proved useful for variable selection in many fields - especially for situations with high-dimensional data where the numbers of predictors far exceeds the number of observations. These methods identify and rank variables of importance but do not generally provide any inference of the selected variables. Thus, the variables selected might be the "most important" but need not be significant. We propose a significance test for the selection found by the Lasso. We introduce a procedure that computes inference and p-values for features chosen by the Lasso. This method rephrases the null hypothesis and uses a randomization approach which ensures that the error rate is controlled even for small samples. We demonstrate the ability of the algorithm to compute p-values of the expected magnitude with simulated data using a multitude of scenarios that involve various effects strengths and correlation between predictors. The algorithm is also applied to a prostate cancer dataset that has been analyzed in recent papers on the subject. The proposed method is found to provide a powerful way to make inference for feature selection even for small samples and when the number of predictors are several orders of magnitude larger than the number of observations. The algorithm is implemented in the MESS package in R and is freely available."]]></description>
<dc:subject>lasso regression via:cshalizi papers variable-selection statistics highdim</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:a8cc712b2f07/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:lasso"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:variable-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:highdim"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1101.0673">
    <title>[1101.0673] Autoregressive Kernels For Time Series</title>
    <dc:date>2014-03-16T06:18:27+00:00</dc:date>
    <link>http://arxiv.org/abs/1101.0673</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We propose in this work a new family of kernels for variable-length time series. Our work builds upon the vector autoregressive (VAR) model for multivariate stochastic processes: given a multivariate time series x, we consider the likelihood function p_{\theta}(x) of different parameters \theta in the VAR model as features to describe x. To compare two time series x and x', we form the product of their features p_{\theta}(x) p_{\theta}(x') which is integrated out w.r.t \theta using a matrix normal-inverse Wishart prior. Among other properties, this kernel can be easily computed when the dimension d of the time series is much larger than the lengths of the considered time series x and x'. It can also be generalized to time series taking values in arbitrary state spaces, as long as the state space itself is endowed with a kernel \kappa. In that case, the kernel between x and x' is a a function of the Gram matrices produced by \kappa on observations and subsequences of observations enumerated in x and x'. We describe a computationally efficient implementation of this generalization that uses low-rank matrix factorization techniques. These kernels are compared to other known kernels using a set of benchmark classification tasks carried out with support vector machines."]]></description>
<dc:subject>statistics via:cshalizi papers time-series kernel-methods .se</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:d8149a7d2077/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:kernel-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.se"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/sjos.12075/abstract?systemMessage=Wiley+Online+Library+will+be+disrupted+Saturday%2C+15+March+from+10%3A00-12%3A00+GMT+%2806%3A00-08%3A00+EDT%29+for+essential+maintenance">
    <title>Likelihood Ratio Tests for Dependent Data with Applications to Longitudinal and Functional Data Analysis - Staicu - 2014 - Scandinavian Journal of Statistics - Wiley Online Library</title>
    <dc:date>2014-03-16T06:07:56+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/sjos.12075/abstract?systemMessage=Wiley+Online+Library+will+be+disrupted+Saturday%2C+15+March+from+10%3A00-12%3A00+GMT+%2806%3A00-08%3A00+EDT%29+for+essential+maintenance</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This paper introduces a general framework for testing hypotheses about the structure of the mean function of complex functional processes. Important particular cases of the proposed framework are as follows: (1) testing the null hypothesis that the mean of a functional process is parametric against a general alternative modelled by penalized splines; and (2) testing the null hypothesis that the means of two possibly correlated functional processes are equal or differ by only a simple parametric function. A global pseudo-likelihood ratio test is proposed, and its asymptotic distribution is derived. The size and power properties of the test are confirmed in realistic simulation scenarios. Finite-sample power results indicate that the proposed test is much more powerful than competing alternatives. Methods are applied to testing the equality between the means of normalized δ-power of sleep electroencephalograms of subjects with sleep-disordered breathing and matched controls."]]></description>
<dc:subject>statistics likelihood hypothesis-testing nonparametrics functional-data-analysis via:cshalizi .se dependent-data</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:c2bf93cf32e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hypothesis-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:functional-data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.se"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:dependent-data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1401.1026">
    <title>[1401.1026] A nonstandard empirical likelihood for time series</title>
    <dc:date>2014-03-10T20:19:38+00:00</dc:date>
    <link>http://arxiv.org/abs/1401.1026</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version of BEL based on a simple, though nonstandard, data-blocking rule which uses a data block of every possible length. Consequently, the method does not involve the usual block selection issues and is also anticipated to exhibit better coverage performance. Its nonstandard blocking scheme, however, induces nonstandard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi-square one, but is distribution-free and can be reproduced through straightforward simulations. Numerical studies indicate that the proposed method generally exhibits better coverage accuracy than standard BEL."]]></description>
<dc:subject>to:NB likelihood time_series statistics via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:9a4b242823cf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1402.1920">
    <title>[1402.1920] Degrees of Freedom and Model Search</title>
    <dc:date>2014-03-03T18:53:52+00:00</dc:date>
    <link>http://arxiv.org/abs/1402.1920</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Degrees of freedom is a fundamental concept in statistical modeling, as it provides a quantitative description of the amount of fitting performed by a given procedure. But, despite this fundamental role in statistics, its behavior not completely well-understood, even in some fairly basic settings. For example, it may seem intuitively obvious that the best subset selection fit with subset size k has degrees of freedom larger than k, but this has not been formally verified, nor has is been precisely studied. In large part, the current paper is motivated by this particular problem, and we derive an exact expression for the degrees of freedom of best subset selection in a restricted setting (orthogonal predictor variables). Along the way, we develop a concept that we name "search degrees of freedom"; intuitively, for adaptive regression procedures that perform variable selection, this is a part of the (total) degrees of freedom that we attribute entirely to the model selection mechanism. Finally, we establish a modest extension of Stein's formula to cover discontinuous functions, and discuss its potential role in degrees of freedom and search degrees of freedom calculations."]]></description>
<dc:subject>papers statistics model-selection degrees-of-freedom via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:bbc5735ae030/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:model-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:degrees-of-freedom"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1402.2499">
    <title>[1402.2499] Justifying Information-Geometric Causal Inference</title>
    <dc:date>2014-02-20T03:21:36+00:00</dc:date>
    <link>http://arxiv.org/abs/1402.2499</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Information Geometric Causal Inference (IGCI) is a new approach to distinguish between cause and effect for two variables. It is based on an independence assumption between input distribution and causal mechanism that can be phrased in terms of orthogonality in information space. We describe two intuitive reinterpretations of this approach that makes IGCI more accessible to a broader audience. "
Moreover, we show that the described independence is related to the hypothesis that unsupervised learning and semi-supervised learning only works for predicting the cause from the effect and not vice versa.]]></description>
<dc:subject>papers causal-inference information-geometry statistics via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:735ee358f2f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:causal-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:information-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/action/showArticleInfo?doi=10.1086%2F674416">
    <title>Laplace’s Demon and the Adventures of His Apprentices</title>
    <dc:date>2014-02-11T03:20:26+00:00</dc:date>
    <link>http://www.jstor.org/action/showArticleInfo?doi=10.1086%2F674416</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["The sensitive dependence on initial conditions (SDIC) associated with nonlinear models imposes limitations on the models’ predictive power. We draw attention to an additional limitation than has been underappreciated, namely, structural model error (SME). A model has SME if the model dynamics differ from the dynamics in the target system. If a nonlinear model has only the slightest SME, then its ability to generate decision-relevant predictions is compromised. Given a perfect model, we can take the effects of SDIC into account by substituting probabilistic predictions for point predictions. This route is foreclosed in the case of SME, which puts us in a worse epistemic situation than SDIC."]]></description>
<dc:subject>prediction chaos misspecification via:cshalizi papers dynamical-systems</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:84e2b2de1e8a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:chaos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:misspecification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://leighphillips.wordpress.com/2013/05/22/dawkins-vs-democracy/">
    <title>Dawkins vs democracy | LEIGH PHILLIPS</title>
    <dc:date>2014-02-04T03:16:54+00:00</dc:date>
    <link>http://leighphillips.wordpress.com/2013/05/22/dawkins-vs-democracy/</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Another famous haranguer of religion, Karl Marx, understood religion to be a protest against real suffering, and that the struggle against religion is pointless without a struggle against a political economy that requires religion as its analgesic. His frequently over-shortened quote, that religion is the opium of the people, continues: ‘The criticism of religion is, therefore, in embryo, the criticism of that vale of tears of which religion is the halo. Criticism has plucked the imaginary flowers on the chain not in order that man shall continue to bear that chain without fantasy or consolation, but so that he shall throw off the chain and pluck the living flower.’
A House of Lords with 25 extra godless scientists is still a House of Lords. The living flower would not have been plucked."]]></description>
<dc:subject>richard-dawkins karl-marx religion democracy via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:e76eef0ae53c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:richard-dawkins"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:karl-marx"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:religion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:democracy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-022513-115657">
    <title>Build, Compute, Critique, Repeat: Data Analysis with Latent Variable Models - Annual Review of Statistics and Its Application, 1(1):203 (David Blei)</title>
    <dc:date>2014-01-09T11:13:02+00:00</dc:date>
    <link>http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-022513-115657</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We survey latent variable models for solving data-analysis problems. A latent variable model is a probabilistic model that encodes hidden patterns in the data. We uncover these patterns from their conditional distribution and use them to summarize data and form predictions. Latent variable models are important in many fields, including computational biology, natural language processing, and social network analysis. Our perspective is that models are developed iteratively: We build a model, use it to analyze data, assess how it succeeds and fails, revise it, and repeat. We describe how new research has transformed these essential activities. First, we describe probabilistic graphical models, a language for formulating latent variable models. Second, we describe mean field variational inference, a generic algorithm for approximating conditional distributions. Third, we describe how to use our analyses to solve problems: exploring the data, forming predictions, and pointing us in the direction of improved models."]]></description>
<dc:subject>papers surveys statistics latent-variables modeling topic-models david-blei via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:f7c0bc28a1dd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:surveys"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:latent-variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:topic-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:david-blei"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-062713-085831">
    <title>Probabilistic Forecasting - Annual Review of Statistics and Its Application, 1(1):125</title>
    <dc:date>2014-01-09T11:09:32+00:00</dc:date>
    <link>http://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-062713-085831</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["A probabilistic forecast takes the form of a predictive probability distribution over future quantities or events of interest. Probabilistic forecasting aims to maximize the sharpness of the predictive distributions, subject to calibration, on the basis of the available information set. We formalize and study notions of calibration in a prediction space setting. In practice, probabilistic calibration can be checked by examining probability integral transform (PIT) histograms. Proper scoring rules such as the logarithmic score and the continuous ranked probability score serve to assess calibration and sharpness simultaneously. As a special case, consistent scoring functions provide decision-theoretically coherent tools for evaluating point forecasts. We emphasize methodological links to parametric and nonparametric distributional regression techniques, which attempt to model and to estimate conditional distribution functions; we use the context of statistically postprocessed ensemble forecasts in numerical weather prediction as an example. Throughout, we illustrate concepts and methodologies in data examples."]]></description>
<dc:subject>papers surveys statistics probability forecasting pediction calibration via:cshalizi .print</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:651a05b387a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:surveys"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:forecasting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:pediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:calibration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:.print"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://alyssafrazee.com/introducing-R.html">
    <title>introducing R to a non-programmer in one hour (alyssa frazee)</title>
    <dc:date>2014-01-08T05:37:57+00:00</dc:date>
    <link>http://alyssafrazee.com/introducing-R.html</link>
    <dc:creator>arsyed</dc:creator><dc:subject>R tutorials via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:efd5ce675756/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:R"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:tutorials"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1312.6168">
    <title>[1312.6168] Factorial Hidden Markov Models for Learning Representations of Natural Language</title>
    <dc:date>2014-01-02T19:14:55+00:00</dc:date>
    <link>http://arxiv.org/abs/1312.6168</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Most representation learning algorithms for language and image processing are local, in that they identify features for a data point based on surrounding points. Yet in language processing, the correct meaning of a word often depends on its global context. As a step toward incorporating global context into representation learning, we develop a representation learning algorithm that incorporates joint prediction into its technique for producing features for a word. We develop efficient variational methods for learning Factorial Hidden Markov Models from large texts, and use variational distributions to produce features for each word that are sensitive to the entire input sequence, not just to a local context window. Experiments on part-of-speech tagging and chunking indicate that the features are competitive with or better than existing state-of-the-art representation learning methods."]]></description>
<dc:subject>via:cshalizi papers nlp hmm grammar-induction variational-inference</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:88adeeae10bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:hmm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:grammar-induction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:variational-inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tandfonline.com/doi/abs/10.1080/01621459.2013.847374#.UrhitaXPUlN">
    <title>Taylor &amp; Francis Online :: A Progressive Block Empirical Likelihood Method for Time Series - Journal of the American Statistical Association - Volume 108, Issue 504</title>
    <dc:date>2013-12-26T08:09:20+00:00</dc:date>
    <link>http://www.tandfonline.com/doi/abs/10.1080/01621459.2013.847374#.UrhitaXPUlN</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["This article develops a new blockwise empirical likelihood (BEL) method for stationary, weakly dependent time processes, called the progressive block empirical likelihood (PBEL). In contrast to the standard version of BEL, which uses data blocks of constant length for a given sample size and whose performance can depend crucially on the block length selection, this new approach involves a data-blocking scheme where blocks increase in length by an arithmetic progression. Consequently, no block length selections are required for the PBEL method, which implies a certain type of robustness for this version of BEL. For inference of smooth functions of the process mean, theoretical results establish the chi-squared limit of the log-likelihood ratio based on PBEL, which can be used to calibrate confidence regions. Using the same progressive block scheme, distributional extensions are also provided for other nonparametric likelihoods with time series in the family of Cressie–Read discrepancies. Simulation evidence indicates that the PBEL method can perform comparably to the standard BEL in coverage accuracy (when the latter uses a “good” block choice) and can exhibit more stability, without the need to select a usual block length. Supplementary materials for this article are available online."]]></description>
<dc:subject>to:NB likelihood statistics statistical_inference_for_stochastic_processes via:cshalizi</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:5c17a3652922/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://omniorthogonal.blogspot.com/2013/12/endarkenment.html">
    <title>Omniorthogonal: Endarkenment</title>
    <dc:date>2013-12-08T20:25:45+00:00</dc:date>
    <link>http://omniorthogonal.blogspot.com/2013/12/endarkenment.html</link>
    <dc:creator>arsyed</dc:creator><dc:subject>neoreactionary politics philosophy via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:c9211eb676fc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:neoreactionary"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1311.2503">
    <title>[1311.2503] Predictable Feature Analysis</title>
    <dc:date>2013-11-18T16:51:39+00:00</dc:date>
    <link>http://arxiv.org/abs/1311.2503</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["Every organism in an environment, whether biological, robotic or virtual, must be able to predict certain aspects of its environment in order to survive or perform whatever task is intended. It needs a model that is capable of estimating the consequences of possible actions, so that planning, control, and decision-making become feasible. For scientific purposes, such models are usually created in a problem specific manner using differential equations and other techniques from control- and system-theory. In contrast to that, we aim for an unsupervised approach that builds up the desired model in a self-organized fashion. Inspired by Slow Feature Analysis (SFA), our approach is to extract sub-signals from the input, that behave as predictable as possible. These "predictable features" are highly relevant for modeling, because predictability is a desired property of the needed consequence-estimating model by definition. In our approach, we measure predictability with respect to a certain prediction model. We focus here on the solution of the arising optimization problem and present a tractable algorithm based on algebraic methods which we call Predictable Feature Analysis (PFA). We prove that the algorithm finds the globally optimal signal, if this signal can be predicted with low error. To deal with cases where the optimal signal has a significant prediction error, we provide a robust, heuristically motivated variant of the algorithm and verify it empirically. Additionally, we give formal criteria a prediction-model must meet to be suitable for measuring predictability in the PFA setting and also provide a suitable default-model along with a formal proof that it meets these criteria."

- Extremely similar to my student Georg Goerg's "forecastable component analysis" (which is duly cited).]]></description>
<dc:subject>prediction statistics via:cshalizi papers time-series</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:1e1ba76af4b8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:time-series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://m.mind.oxfordjournals.org/content/early/2013/10/31/mind.fzt073.full?keytype=ref&amp;ijkey=JaKp6eczj44oA1I">
    <title>Basic Structures of Reality: Essays in Meta-Physics, by Colin McGinn.</title>
    <dc:date>2013-11-04T20:14:00+00:00</dc:date>
    <link>http://m.mind.oxfordjournals.org/content/early/2013/10/31/mind.fzt073.full?keytype=ref&amp;ijkey=JaKp6eczj44oA1I</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["For all the epistemic faux-modesty that this book purports to defend, the image that persists while grinding through its pages is of an individual ludicrously fancying themselves as uniquely positioned to solve the big questions for us, from scratch and unassisted, as if none of the rest of us working in the field have had anything worth a damn to contribute. It will however be clear by now that I take the reality to be substantially different."]]></description>
<dc:subject>books reviews philosophy physics colin-mcginn via:cshalizi</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:arsyed/b:fd74d55731ff/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:reviews"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:colin-mcginn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1310.4210">
    <title>[1310.4210] Demystifying Information-Theoretic Clustering</title>
    <dc:date>2013-10-23T19:56:09+00:00</dc:date>
    <link>http://arxiv.org/abs/1310.4210</link>
    <dc:creator>arsyed</dc:creator><description><![CDATA["We propose a novel method for clustering data which is grounded in information-theoretic principles and requires no parametric assumptions. Previous attempts to use information theory to define clusters in an assumption-free way are based on maximizing mutual information between data and cluster labels. We demonstrate that this intuition suffers from a fundamental conceptual flaw that causes clustering performance to deteriorate as the amount of data increases. Instead, we return to the axiomatic foundations of information theory to define a meaningful clustering measure based on the notion of consistency under coarse-graining for finite data."]]></description>
<dc:subject>clustering statistics via:cshalizi papers information-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:arsyed/b:fbec1b7e0e6d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:arsyed/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>