<?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 (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://arxiv.org/abs/1905.11744"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1558512018"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.05506"/>
	<rdf:li rdf:resource="http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00870"/>
	<rdf:li rdf:resource="http://www.cims.nyu.edu/~vitaly/pub/fts.pdf"/>
	<rdf:li rdf:resource="http://www.cambridge.org/us/academic/subjects/statistics-probability/applied-probability-and-stochastic-networks/ergodic-control-diffusion-processes?format=HB"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0707.0322"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1401.0304"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1309.1007"/>
	<rdf:li rdf:resource="http://www.jstor.org/stable/2984809"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1305.5618"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1212.5796"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ejs/1349355603"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1338515139"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1202.4283"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1111.1876"/>
	<rdf:li rdf:resource="http://www.springerlink.com/content/c38664053l348582/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1110.2529"/>
	<rdf:li rdf:resource="http://www.cs.princeton.edu/~satyen/papers/crossvalidation.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1011.0096"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aop/1278593952"/>
	<rdf:li rdf:resource="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1327806"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1005.5603"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ssu/1268143839"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1176347266"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v2/bousquet02a.html"/>
	<rdf:li rdf:resource="http://www.springerlink.com/content/6pn026181h87uv7m/"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271619"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271609"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0912.4480"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v10/zakai09a.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0902.2924"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v5/grandvalet04a.html"/>
	<rdf:li rdf:resource="http://www.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2009.187"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0911.3083"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0911.1497"/>
	<rdf:li rdf:resource="http://www.springerlink.com/content/mh1021k5g8751527/"/>
	<rdf:li rdf:resource="http://www3.interscience.wiley.com/journal/118490759/abstract"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0906.0791"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v10/jiang09a.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0811.1629"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0903.1721"/>
	<rdf:li rdf:resource="http://www.math.lsa.umich.edu/~barvinok/total710.pdf"/>
	<rdf:li rdf:resource="http://cbcl.mit.edu/projects/cbcl/publications/ps/mukherjee-ACM-06.pdf"/>
	<rdf:li rdf:resource="http://www.springerlink.com/content/e00283104305r8g5/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0806.2941"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/1905.11744">
    <title>[1905.11744] Evaluating time series forecasting models: An empirical study on performance estimation methods</title>
    <dc:date>2019-05-29T20:01:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.11744</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Performance estimation aims at estimating the loss that a predictive model will incur on unseen data. These procedures are part of the pipeline in every machine learning project and are used for assessing the overall generalisation ability of predictive models. In this paper we address the application of these methods to time series forecasting tasks. For independent and identically distributed data the most common approach is cross-validation. However, the dependency among observations in time series raises some caveats about the most appropriate way to estimate performance in this type of data and currently there is no settled way to do so. We compare different variants of cross-validation and of out-of-sample approaches using two case studies: One with 62 real-world time series and another with three synthetic time series. Results show noticeable differences in the performance estimation methods in the two scenarios. In particular, empirical experiments suggest that cross-validation approaches can be applied to stationary time series. However, in real-world scenarios, when different sources of non-stationary variation are at play, the most accurate estimates are produced by out-of-sample methods that preserve the temporal order of observations."]]></description>
<dc:subject>to:NB time_series prediction cross-validation model_selection re:XV_for_mixing statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ed717cceb1c1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1558512018">
    <title>Richter , Dahlhaus : Cross validation for locally stationary processes</title>
    <dc:date>2019-05-26T22:29:21+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1558512018</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose an adaptive bandwidth selector via cross validation for local M-estimators in locally stationary processes. We prove asymptotic optimality of the procedure under mild conditions on the underlying parameter curves. The results are applicable to a wide range of locally stationary processes such linear and nonlinear processes. A simulation study shows that the method works fairly well also in misspecified situations."]]></description>
<dc:subject>to:NB cross-validation nonparametrics statistics non-stationarity re:XV_for_mixing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:40c83ead576d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-stationarity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.05506">
    <title>[1607.05506] Distribution-dependent concentration inequalities for tighter generalization bounds</title>
    <dc:date>2016-11-24T21:10:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.05506</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We prove several distribution-dependent extensions of Hoeffding and McDiarmid's inequalities with (difference-) unbounded and hierarchically (difference-) bounded functions. For this purpose, several assumptions about the probabilistic boundedness and bounded differences are introduced. Our approaches improve the previous concentration inequalities' bounds, and achieve tight bounds in some exceptional cases where the original inequalities cannot hold. Furthermore, we discuss the potential applications of our extensions in VC dimension and Rademacher complexity. Then we obtain generalization bounds for (difference-) unbounded loss functions and tighten the existing generalization bounds."]]></description>
<dc:subject>learning_theory deviation_inequalities stochastic_processes statistics re:XV_for_mixing in_NB to_teach:childs_garden_of_statistical_learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9423345a6312/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00870">
    <title>Learning Theory Estimates with Observations from General Stationary Stochastic Processes | Neural Computation | MIT Press Journals</title>
    <dc:date>2016-11-23T18:21:15+00:00</dc:date>
    <link>http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00870</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This letter investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by general, we mean that many stationary stochastic processes can be included. We show that when the stochastic processes satisfy a generalized Bernstein-type inequality, a unified treatment on analyzing the learning schemes with various mixing processes can be conducted and a sharp oracle inequality for generic regularized empirical risk minimization schemes can be established. The obtained oracle inequality is then applied to derive convergence rates for several learning schemes such as empirical risk minimization (ERM), least squares support vector machines (LS-SVMs) using given generic kernels, and SVMs using gaussian kernels for both least squares and quantile regression. It turns out that for independent and identically distributed (i.i.d.) processes, our learning rates for ERM recover the optimal rates. For non-i.i.d. processes, including geometrically -mixing Markov processes, geometrically -mixing processes with restricted decay, -mixing processes, and (time-reversed) geometrically -mixing processes, our learning rates for SVMs with gaussian kernels match, up to some arbitrarily small extra term in the exponent, the optimal rates. For the remaining cases, our rates are at least close to the optimal rates. As a by-product, the assumed generalized Bernstein-type inequality also provides an interpretation of the so-called effective number of observations for various mixing processes."]]></description>
<dc:subject>stochastic_processes learning_theory dependence_measures mixing ergodic_theory statistics re:XV_for_mixing re:your_favorite_dsge_sucks in_NB to_teach:childs_garden_of_statistical_learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5c929691bae6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dependence_measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cims.nyu.edu/~vitaly/pub/fts.pdf">
    <title>Forecasting Nonstationary Time Series: From Theory to Algorithms</title>
    <dc:date>2014-12-17T18:09:44+00:00</dc:date>
    <link>http://www.cims.nyu.edu/~vitaly/pub/fts.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Generalization bounds for time series prediction and other non-i.i.d. learning sce- narios that can be found in the machine learning and statistics literature assume that observations come from a (strictly) stationary distribution. The first bounds for completely non-stationary setting were proved in [6]. In this work we present an extension of these results and derive novel algorithms for forecasting non- stationary time series. Our experimental results show that our algorithms sig- nificantly outperform standard autoregressive models commonly used in practice."

--- Assumes mixing but not stationary.]]></description>
<dc:subject>to:NB mixing learning_theory re:your_favorite_dsge_sucks re:XV_for_mixing time_series have_read to_teach:childs_garden_of_statistical_learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5aee25e7a5fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cambridge.org/us/academic/subjects/statistics-probability/applied-probability-and-stochastic-networks/ergodic-control-diffusion-processes?format=HB">
    <title>Ergodic Control of Diffusion Processes | Applied probability and stochastic networks | Cambridge University Press</title>
    <dc:date>2014-03-27T15:52:31+00:00</dc:date>
    <link>http://www.cambridge.org/us/academic/subjects/statistics-probability/applied-probability-and-stochastic-networks/ergodic-control-diffusion-processes?format=HB</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This comprehensive volume on ergodic control for diffusions highlights intuition alongside technical arguments. A concise account of Markov process theory is followed by a complete development of the fundamental issues and formalisms in control of diffusions. This then leads to a comprehensive treatment of ergodic control, a problem that straddles stochastic control and the ergodic theory of Markov processes. The interplay between the probabilistic and ergodic-theoretic aspects of the problem, notably the asymptotics of empirical measures on one hand, and the analytic aspects leading to a characterization of optimality via the associated Hamilton–Jacobi–Bellman equation on the other, is clearly revealed. The more abstract controlled martingale problem is also presented, in addition to many other related issues and models. Assuming only graduate-level probability and analysis, the authors develop the theory in a manner that makes it accessible to users in applied mathematics, engineering, finance and operations research."

- Relevant to defining risk properly for forecasting?]]></description>
<dc:subject>books:noted stochastic_processes ergodic_theory re:XV_for_mixing in_NB control_theory_and_control_engineering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bde861070652/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:control_theory_and_control_engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0707.0322">
    <title>[0707.0322] Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise</title>
    <dc:date>2014-03-12T20:37:56+00:00</dc:date>
    <link>http://arxiv.org/abs/0707.0322</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of forecasting the next (observable) state of an unknown ergodic dynamical system from a noisy observation of the present state. Our main result shows, for example, that support vector machines (SVMs) using Gaussian RBF kernels can learn the best forecaster from a sequence of noisy observations if (a) the unknown observational noise process is bounded and has a summable α-mixing rate and (b) the unknown ergodic dynamical system is defined by a Lipschitz continuous function on some compact subset of ℝd and has a summable decay of correlations for Lipschitz continuous functions. In order to prove this result we first establish a general consistency result for SVMs and all stochastic processes that satisfy a mixing notion that is substantially weaker than α-mixing."]]></description>
<dc:subject>dynamical_systems mixing ergodic_theory nonparametrics statistics prediction support-vector_machines steinwart.ingo time_series statistical_inference_for_stochastic_processes re:your_favorite_dsge_sucks re:XV_for_mixing to_read in_NB entableted</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a11e92b7fc51/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:support-vector_machines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:steinwart.ingo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:entableted"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1401.0304">
    <title>[1401.0304] Learning without Concentration</title>
    <dc:date>2014-01-04T19:44:55+00:00</dc:date>
    <link>http://arxiv.org/abs/1401.0304</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We obtain sharp bounds on the performance of Empirical Risk Minimization performed in a convex class and with respect to the squared loss, without any boundedness assumptions on class members or on the target. Rather than resorting to a concentration-based argument, the method relies on a `small-ball' assumption and thus holds for heavy-tailed sampling and heavy-tailed targets. Moreover, the resulting estimates scale correctly with the `noise'. When applied to the classical, bounded scenario, the method always improves the known estimates."]]></description>
<dc:subject>learning_theory re:your_favorite_dsge_sucks re:XV_for_mixing have_read in_NB to_teach:childs_garden_of_statistical_learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4be5cac1cead/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1309.1007">
    <title>[1309.1007] Concentration in unbounded metric spaces and algorithmic stability</title>
    <dc:date>2013-09-05T12:48:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1309.1007</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We prove an extension of McDiarmid's inequality for metric spaces with unbounded diameter. To this end, we introduce the notion of the {\em subgaussian diameter}, which is a distribution-dependent refinement of the metric diameter. Our technique provides an alternative approach to that of Kutin and Niyogi's method of weakly difference-bounded functions, and yields nontrivial, dimension-free results in some interesting cases where the former does not. As an application, we give apparently the first generalization bound in the algorithmic stability setting that holds for unbounded loss functions. We furthermore extend our concentration inequality to strongly mixing processes."]]></description>
<dc:subject>concentration_of_measure stability_of_learning learning_theory probability kontorovich.aryeh kith_and_kin re:XV_for_mixing re:your_favorite_dsge_sucks have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2636de015e38/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kontorovich.aryeh"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/stable/2984809">
    <title>Cross-Validatory Choice and Assessment of Statistical Predictions</title>
    <dc:date>2013-08-13T20:12:22+00:00</dc:date>
    <link>http://www.jstor.org/stable/2984809</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A generalized form of the cross-validation criterion is applied to the choice and assessment of prediction using the data-analytic concept of a prescription. The examples used to illustrate the application are drawn from the problem areas of univariate estimation, linear regression and analysis of variance."]]></description>
<dc:subject>have_read cross-validation statistics prediction re:XV_for_mixing re:XV_for_networks re:stacs to_teach:undergrad-ADA in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:31be6815120e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:stacs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1305.5618">
    <title>[1305.5618] A general approach to the joint asymptotic analysis of statistics from sub-samples</title>
    <dc:date>2013-05-27T12:15:21+00:00</dc:date>
    <link>http://arxiv.org/abs/1305.5618</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In time series analysis, statistics based on collections of estimators computed from sub-samples play a crucial role in an increasing variety of important applications. Proving results about the joint asymptotic distribution of such statistics is challenging since it typically involves a nontrivial verification of technical conditions and tedious case-by-case asymptotic analysis. In this paper, we provide a novel technique that allows to circumvent those problems in a general setting. Our approach consists of two major steps: a probabilistic part which is mainly concerned with weak convergence of sequential empirical processes, and an analytic part providing general ways to extend this weak convergence to functionals of the sequential empirical process. Our theory provides a unified treatment of asymptotic distributions for a large class of statistics, including recently proposed self-normalized statistics and sub-sampling based p-values. In addition, we comment on the consistency of bootstrap procedures and obtain general results on compact differentiability of certain mappings that seem to be of independent interest."]]></description>
<dc:subject>to_read re:XV_for_mixing empirical_processes bootstrap time_series convergence_of_stochastic_processes statistical_inference_for_stochastic_processes statistics in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dac13484b7b7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:convergence_of_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1212.5796">
    <title>[1212.5796] On the method of typical bounded differences</title>
    <dc:date>2012-12-27T18:09:15+00:00</dc:date>
    <link>http://arxiv.org/abs/1212.5796</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Concentration inequalities are fundamental tools in probabilistic combinatorics and theoretical computer science for proving that random functions are near their means. Of particular importance is the case where f(X) is a function of independent random variables X=(X_1, ..., X_n). Here the well known bounded differences inequality (also called McDiarmid's or Hoeffding-Azuma inequality) establishes sharp concentration if the function f does not depend too much on any of the variables. One attractive feature is that it relies on a very simple Lipschitz condition (L): it suffices to show that |f(X)-f(X')| leq c_k whenever X,X' differ only in X_k. While this is easy to check, the main disadvantage is that it considers worst-case changes c_k, which often makes the resulting bounds too weak to be useful. 
"In this paper we prove a variant of the bounded differences inequality which can be used to establish concentration of functions f(X) where (i) the typical changes are small although (ii) the worst case changes might be very large. One key aspect of this inequality is that it relies on a simple condition that (a) is easy to check and (b) coincides with heuristic considerations why concentration should hold. Indeed, given an event Gamma that holds with very high probability, we essentially relax the Lipschitz condition (L) to situations where Gamma occurs. The point is that the resulting typical changes c_k are often much smaller than the worst case ones. 
"To illustrate its application we consider the reverse H-free process, where H is 2-balanced. We prove that the final number of edges in this process is concentrated, and also determine its likely value up to constant factors. This answers a question of Bollob'as and ErdH{o}s."]]></description>
<dc:subject>to_read probability concentration_of_measure re:almost_none re:your_favorite_dsge_sucks re:XV_for_mixing re:XV_for_networks in_NB deviation_inequalities</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:20c0c9aa7555/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ejs/1349355603">
    <title>Lecué , Mitchell : Oracle inequalities for cross-validation type procedures</title>
    <dc:date>2012-10-04T14:47:25+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ejs/1349355603</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We prove oracle inequalities for three different types of adaptation procedures inspired by cross-validation and aggregation. These procedures are then applied to the construction of Lasso estimators and aggregation with exponential weights with data-driven regularization and temperature parameters, respectively. We also prove oracle inequalities for the cross-validation procedure itself under some convexity assumptions."

--- It seems to me that their example 2.8, of a case where un-modified CV will do badly, is rather cheating, because the two estimators change behavior as the sample size changes without rhyme or reason.  (They're almost "grue" and "bleen", actually.)  I'm not sure how exactly to phrase this mathematically.]]></description>
<dc:subject>cross-validation statistics re:XV_for_mixing re:XV_for_networks have_read empirical_processes in_NB lasso ensemble_methods</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a711e9e5dfa3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lasso"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1338515139">
    <title>Lecué , Mendelson : General nonexact oracle inequalities for classes with a subexponential envelope</title>
    <dc:date>2012-06-01T14:12:36+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1338515139</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We show that empirical risk minimization procedures and regularized empirical risk minimization procedures satisfy nonexact oracle inequalities in an unbounded framework, under the assumption that the class has a subexponential envelope function. The main novelty, in addition to the boundedness assumption free setup, is that those inequalities can yield fast rates even in situations in which exact oracle inequalities only hold with slower rates.
"We apply these results to show that procedures based on $ell_{1}$ and nuclear norms regularization functions satisfy oracle inequalities with a residual term that decreases like $1/n$ for every $L_{q}$-loss functions ($qgeq2$), while only assuming that the tail behavior of the input and output variables are well behaved. In particular, no RIP type of assumption or “incoherence condition” are needed to obtain fast residual terms in those setups. We also apply these results to the problems of convex aggregation and model selection."

This looks awesome.]]></description>
<dc:subject>to_read learning_theory model_selection statistics re:your_favorite_dsge_sucks re:XV_for_mixing ensemble_methods lecue.guillaume mendelson.shahar in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:723d702bf01d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lecue.guillaume"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mendelson.shahar"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1202.4283">
    <title>[1202.4283] Fast rates in learning with dependent observations</title>
    <dc:date>2012-02-21T03:42:32+00:00</dc:date>
    <link>http://arxiv.org/abs/1202.4283</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we tackle the problem of fast rates in time series forecasting from a statistical learning perspective. In a serie of papers (e.g. Meir 2000, Modha and Masry 1998, Alquier and Wintenberger 2012) it is shown that the main tools used in learning theory with iid observations can be extended to the prediction of time series. The main message of these papers is that, given a family of predictors, we are able to build a new predictor that predicts the series as well as the best predictor in the family, up to a remainder of order $1/sqrt{n}$. It is known that this rate cannot be improved in general. In this paper, we show that in the particular case of the least square loss, and under a strong assumption on the time series (phi-mixing) the remainder is actually of order $1/n$. Thus, the optimal rate for iid variables, see e.g. Tsybakov 2003, and individual sequences, see cite{lugosi} is, for the first time, achieved for uniformly mixing processes. We also show that our method is optimal for aggregating sparse linear combinations of predictors."

--- Assumes observations are in the interval [-B,B] and gets a bound which is O(B^3), and so useless for our purposes.]]></description>
<dc:subject>learning_theory mixing ergodic_theory re:your_favorite_dsge_sucks re:XV_for_mixing have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d4316c2a0b5b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1111.1876">
    <title>[1111.1876] On the stability of bootstrap estimators</title>
    <dc:date>2011-11-09T14:16:53+00:00</dc:date>
    <link>http://arxiv.org/abs/1111.1876</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It is shown that bootstrap approximations of an estimator which is based on a continuous operator from the set of Borel probability measures defined on a compact metric space into a complete separable metric space is stable in the sense of qualitative robustness. Support vector machines based on shifted loss functions are treated as special cases."]]></description>
<dc:subject>statistics bootstrap stability_of_learning re:XV_for_mixing in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:acc1df906317/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.springerlink.com/content/c38664053l348582/">
    <title>A Bernstein type inequality and moderate deviations for weakly dependent sequences</title>
    <dc:date>2011-11-07T18:56:14+00:00</dc:date>
    <link>http://www.springerlink.com/content/c38664053l348582/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we present a Bernstein-type tail inequality for the maximum of partial sums of a weakly dependent sequence of random variables that is not necessarily bounded. The class considered includes geometrically and subgeometrically strongly mixing sequences. The result is then used to derive asymptotic moderate deviation results. Applications are given for classes of Markov chains, iterated Lipschitz models and functions of linear processes with absolutely regular innovations."  Also: http://arxiv.org/abs/0902.0582]]></description>
<dc:subject>to_read re:XV_for_mixing re:your_favorite_dsge_sucks concentration_of_measure mixing ergodic_theory stochastic_processes moderate_deviations in_NB deviation_inequalities</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:23f7c782d807/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:moderate_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1110.2529">
    <title>[1110.2529] The Generalization Ability of Online Algorithms for Dependent Data</title>
    <dc:date>2011-10-13T12:33:26+00:00</dc:date>
    <link>http://arxiv.org/abs/1110.2529</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the generalization performance of arbitrary online learning algorithms trained on samples coming from a dependent source of data. We show that the generalization error of any stable online algorithm concentrates around its regret--an easily computable statistic of the online performance of the algorithm--when the underlying ergodic process is $beta$- or $phi$-mixing. We show high probability error bounds assuming the loss function is convex, and we also establish sharp convergence rates and deviation bounds for strongly convex losses and several linear prediction problems such as linear and logistic regression, least-squares SVM, and boosting on dependent data. In addition, our results have straightforward applications to stochastic optimization with dependent data, and our analysis requires only martingale convergence arguments; we need not rely on more powerful statistical tools such as empirical process theory."]]></description>
<dc:subject>learning_theory individual_sequence_prediction ergodic_theory mixing re:growing_ensemble_project re:XV_for_mixing stability_of_learning concentration_of_measure have_read re:your_favorite_dsge_sucks in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0891bd9c9846/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:individual_sequence_prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:growing_ensemble_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.princeton.edu/~satyen/papers/crossvalidation.pdf">
    <title>Cross-Validation and Mean-Square Stability</title>
    <dc:date>2011-03-06T14:33:04+00:00</dc:date>
    <link>http://www.cs.princeton.edu/~satyen/papers/crossvalidation.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[It's a little boggling that they don't cite any of the modern (2000--) work on theoretical properties of CV, but oh well...
]]></description>
<dc:subject>cross-validation learning_theory stability_of_learning statistics re:your_favorite_dsge_sucks re:XV_for_mixing re:XV_for_networks to_read via:nikete</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3fe38f8cc113/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:nikete"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1011.0096">
    <title>[1011.0096] Concentration inequalities of the cross-validation estimator for Empirical Risk Minimiser</title>
    <dc:date>2010-11-04T21:02:29+00:00</dc:date>
    <link>http://arxiv.org/abs/1011.0096</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>learning_theory model_selection cross-validation to_read re:XV_for_mixing re:XV_for_networks</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:96bb8d8125e6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aop/1278593952">
    <title>Adams, Nobel: Uniform convergence of Vapnik–Chervonenkis classes under ergodic sampling</title>
    <dc:date>2010-07-08T14:01:58+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aop/1278593952</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Oooh: "We show that if X is a complete separable metric space and C  is a countable family of Borel subsets of  with finite VC dimension, then, for every stationary ergodic process with values in X, the relative frequencies of sets c \in C converge uniformly to their limiting probabilities. Beyond ergodicity, no assumptions are imposed on the sampling process, and no regularity conditions are imposed on the elements of C. The result extends existing work of Vapnik and Chervonenkis, among others, who have studied uniform convergence for i.i.d. and strongly mixing processes. Our method of proof is new and direct: it does not rely on symmetrization techniques, probability inequalities or mixing conditions. The uniform convergence of relative frequencies for VC-major and VC-graph classes of functions under ergodic sampling is established as a corollary of the basic result for sets."  No rates, but very nice.
]]></description>
<dc:subject>ergodic_theory learning_theory stochastic_processes vc-dimension have_read re:XV_for_mixing re:your_favorite_dsge_sucks</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cc75398c017c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:vc-dimension"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1327806">
    <title>IEEE Xplore - On the generalization ability of on-line learning algorithms</title>
    <dc:date>2010-07-01T14:15:30+00:00</dc:date>
    <link>http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1327806</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on [IID data]. ... a simple large deviation argument [proves] tight data-dependent bounds for the risk of this hypothesis in terms of an easily computable statistic Mn associated with the on-line performance of the ensemble. Via sharp pointwise bounds on Mn, we then obtain risk tail bounds for kernel perceptron algorithms in terms of the spectrum of the empirical kernel matrix. ... A distinctive feature of our approach is that the key tools for our analysis come from the model of prediction of individual sequences; i.e., a model making no probabilistic assumptions on the source generating the data. In fact, these tools turn out to be so powerful that we only need very elementary statistical facts to obtain our final risk bounds."  Bounced off this 2004; try again.
]]></description>
<dc:subject>learning_theory large_deviations online_learning individual_sequence_prediction via:djm1107 re:your_favorite_dsge_sucks re:XV_for_mixing ensemble_methods have_read low-regret_learning</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:45e79ffb4005/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:online_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:individual_sequence_prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:djm1107"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:low-regret_learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1005.5603">
    <title>[1005.5603] Sequence prediction in realizable and non-realizable cases</title>
    <dc:date>2010-06-01T14:25:12+00:00</dc:date>
    <link>http://arxiv.org/abs/1005.5603</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>prediction time_series statistics universal_prediction to_read re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6521217d467d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:universal_prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ssu/1268143839">
    <title>Arlot, Celisse: A survey of cross-validation procedures for model selection</title>
    <dc:date>2010-03-09T14:46:54+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ssu/1268143839</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to_read cross-validation model_selection statistics re:XV_for_mixing re:XV_for_networks arlot.sylvain</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ec45badb5091/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:arlot.sylvain"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1176347266">
    <title>Boente, Fraiman: Robust Nonparametric Regression Estimation for Dependent Observations</title>
    <dc:date>2010-03-03T22:04:20+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1176347266</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Robust nonparametric estimators for regression and autoregression are proposed for $\varphi$- and $\alpha$-mixing processes. Two families of $M$-type robust equivariant estimators are considered: (i) estimators based on kernel methods and (ii) estimators based on $k$-nearest neighbor kernel methods. Strong consistency of both families is proved under mild conditions. For the first class the result is true under no assumptions whatsoever on the distribution of the observations."
]]></description>
<dc:subject>statistical_inference_for_stochastic_processes regression estimation re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1ac62e852de8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v2/bousquet02a.html">
    <title>Stability and Generalization (Bousquet and Elisseeff, 2002)</title>
    <dc:date>2010-02-14T17:51:29+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v2/bousquet02a.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Odd that they don't mention Domingos's "proces-oriented evaluation".
]]></description>
<dc:subject>learning_theory statistics hilbert_space re:your_favorite_dsge_sucks re:XV_for_mixing re:XV_for_networks have_read</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fa5f30820c7b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hilbert_space"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.springerlink.com/content/6pn026181h87uv7m/">
    <title>The generalization performance of ERM algorithm with strongly mixing observations</title>
    <dc:date>2010-02-14T15:30:25+00:00</dc:date>
    <link>http://www.springerlink.com/content/6pn026181h87uv7m/</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistical_inference_for_stochastic_processes learning_theory ergodic_theory to_read re:XV_for_mixing re:AoS_project re:your_favorite_dsge_sucks</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9be27acd0996/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271619">
    <title>Lahiri: Edgeworth expansions for studentized statistics under weak dependence</title>
    <dc:date>2009-12-31T16:46:03+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271619</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistical_inference_for_stochastic_processes statistics mixing stochastic_processes to_read re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:17c16458da7a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271609">
    <title>Arlot, Blanchard, Roquain: Some nonasymptotic results on resampling in high dimension, I: Confidence regions</title>
    <dc:date>2009-12-31T16:43:40+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1262271609</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study generalized bootstrap confidence regions for the mean of a random vector whose coordinates have an unknown dependency structure. The random vector is supposed to be either Gaussian or to have a symmetric and bounded distribution. The dimensionality of the vector can possibly be much larger than the number of observations and we focus on a nonasymptotic control of the confidence level, following ideas inspired by recent results in learning theory. We consider two approaches, the first based on a concentration principle (valid for a large class of resampling weights) and the second on a resampled quantile, specifically using Rademacher weights. Several intermediate results established in the approach based on concentration principles are of interest in their own right. We also discuss the question of accuracy when using Monte Carlo approximations of the resampled quantities."
]]></description>
<dc:subject>statistics resampling bootstrap cross-validation confidence_sets to_read re:XV_for_mixing concentration_of_measure learning_theory</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:803ef86dd7c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:resampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0912.4480">
    <title>[0912.4480] Consistency of the Maximum Likelihood Estimator for general hidden Markov models</title>
    <dc:date>2009-12-28T16:25:44+00:00</dc:date>
    <link>http://arxiv.org/abs/0912.4480</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["a parametrized family of general hidden Markov models, where both the observed and unobserved components take values in a complete separable metric space. We prove that the maximum likelihood estimator (MLE) of the parameter is strongly consistent under a rather minimal set of assumptions. As special cases of our main result, we obtain consistency in a large class of nonlinear state space models, as well as general results on linear Gaussian state space models and finite state models. A novel aspect of our approach is an information-theoretic technique for proving identifiability, which does not require an explicit representation for the relative entropy rate. Our method of proof could therefore form a foundation for the investigation of MLE consistency in more general dependent and non-Markovian time series. Also of independent interest is a general concentration inequality for $V$-uniformly ergodic Markov chains."
]]></description>
<dc:subject>markov_models statistics estimation concentration_of_measure information_theory identifiability re:AoS_project re:XV_for_mixing have_read</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f8aea4e331ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:identifiability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v10/zakai09a.html">
    <title>Consistency and Localizability</title>
    <dc:date>2009-12-28T15:19:05+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v10/zakai09a.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We show that all consistent learning methods---that is, that asymptotically achieve the lowest possible expected loss for any distribution on (X,Y)---are necessarily localizable, by which we mean that they do not significantly change their response at a particular point when we show them only the part of the training set that is close to that point. This is true in particular for methods that appear to be defined in a non-local manner, such as support vector machines in classification and least-squares estimators in regression. Aside from showing that consistency implies a specific form of localizability, we also show that consistency is logically equivalent to the combination of two properties: (1) a form of localizability, and (2) that the method's global mean (over the entire X distribution) correctly estimates the true mean. Consistency can therefore be seen as comprised of two aspects, one local and one global."  Feels like it should connect to cross-validation.
]]></description>
<dc:subject>statistics machine_learning learning_theory consistency to_read re:XV_for_networks re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8f5c248af2d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:consistency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0902.2924">
    <title>[0902.2924] Model selection and randomization for weakly dependent time series forecasting</title>
    <dc:date>2009-12-26T23:53:58+00:00</dc:date>
    <link>http://arxiv.org/abs/0902.2924</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Observing a stationary time series, we propose a two-steps procedure for the prediction of its next value. The first step follows machine learning theory paradigm and consists in determining a set of possible predictors as randomized estimators in (possibly numerous) different predictive models. The second step follows the model selection paradigm and consists in choosing one predictor with good properties among all the predictors of the first step. We study our procedure for two different types of observations: causal Bernoulli shifts and bounded weakly dependent processes. In both cases, we give oracle inequalities: the risk of the chosen predictor is close to the best prediction risk in all predictive models that we consider. We apply our procedure for predictive models as linear predictors, neural networks predictors and nonparametric autoregressive predictors."

Published version: http://projecteuclid.org/euclid.bj/1340887007]]></description>
<dc:subject>time_series prediction model_selection ensemble_methods re:AoS_project re:XV_for_mixing have_read in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:33862efff659/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v5/grandvalet04a.html">
    <title>No Unbiased Estimator of the Variance of K-Fold Cross-Validation (Bengio and Grandvalet, 2004)</title>
    <dc:date>2009-11-20T14:58:35+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v5/grandvalet04a.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>machine_learning statistics cross-validation model_selection to_read to_teach:data-mining re:XV_for_networks re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fd653ac3e95d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2009.187">
    <title>Sensitivity Analysis of k-fold Cross-Validation in Prediction Error Estimation</title>
    <dc:date>2009-11-20T01:33:55+00:00</dc:date>
    <link>http://www.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2009.187</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Apparently IEEE makes this available solely to tease me, since, while we have a fully paid-up electronic subscription, I can't get access.
]]></description>
<dc:subject>machine_learning statistics cross-validation to_read re:XV_for_mixing re:XV_for_networks</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f4600b1c2c52/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0911.3083">
    <title>[0911.3083] Bootstrap for the Sample Mean and for U-Statistics of Stationary Processes</title>
    <dc:date>2009-11-19T13:53:38+00:00</dc:date>
    <link>http://arxiv.org/abs/0911.3083</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistics time_series statistical_inference_for_stochastic_processes bootstrap dynamical_systems to_read re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:49b62e6523b3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0911.1497">
    <title>[0911.1497] Optimal model selection for density estimation of stationary data under various mixing conditions</title>
    <dc:date>2009-11-10T03:57:20+00:00</dc:date>
    <link>http://arxiv.org/abs/0911.1497</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistics statistical_inference_for_stochastic_processes mixing model_selection re:XV_for_mixing density_estimation</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d00b9fae124b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:density_estimation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.springerlink.com/content/mh1021k5g8751527/">
    <title>A Hoeffding-Type Inequality for Ergodic Time Series (Tang, 2007)</title>
    <dc:date>2009-09-07T13:16:58+00:00</dc:date>
    <link>http://www.springerlink.com/content/mh1021k5g8751527/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, a Hoeffding-type inequality is presented for a class of ergodic time series. The inequality is then used to construct uniformly exponentially consistent tests, which are useful tools for studying Bayesian consistency."  Preprint at http://www4.stat.ncsu.edu/~sghosal/papers/Tang.pdf, haven't compared.
]]></description>
<dc:subject>ergodic_theory hoeffdings_inequality time_series have_read re:XV_for_mixing deviation_inequalities</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f7150adb9235/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hoeffdings_inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www3.interscience.wiley.com/journal/118490759/abstract">
    <title>Probabilistic forecasts, calibration and sharpness</title>
    <dc:date>2009-07-21T13:44:46+00:00</dc:date>
    <link>http://www3.interscience.wiley.com/journal/118490759/abstract</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>prediction statistics cross-validation ensemble_methods calibration to_read re:XV_for_mixing re:XV_for_networks to_teach:undergrad-ADA</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ee272b8a726b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:calibration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0906.0791">
    <title>[0906.0791] Instability statistics and mixing rates</title>
    <dc:date>2009-06-05T15:18:45+00:00</dc:date>
    <link>http://arxiv.org/abs/0906.0791</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We claim that looking at probability distributions of emph{finite time} largest Lyapunov exponents, and more precisely studying their large deviation properties, yields an extremely powerful technique to get quantitative estimates of polynomial decay rates of time correlations and Poincar'e recurrences in the -quite delicate- case of dynamical systems with weak chaotic properties."
]]></description>
<dc:subject>dynamical_systems large_deviations poincare_recurrence mixing ergodic_theory to_read re:XV_for_mixing in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0eefa020f839/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:poincare_recurrence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v10/jiang09a.html">
    <title>On Uniform Deviations of General Empirical Risks with Unboundedness, Dependence, and High Dimensionality</title>
    <dc:date>2009-05-03T14:12:21+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v10/jiang09a.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The statistical learning theory of risk minimization depends heavily on probability bounds for uniform deviations of the empirical risks. Classical probability bounds using Hoeffding's inequality cannot accommodate more general situations with unbounded loss and dependent data. The current paper introduces an inequality that extends Hoeffding's inequality to handle these more general situations. We will apply this inequality to provide probability bounds for uniform deviations in a very general framework, which can involve discrete decision rules, unbounded loss, and a dependence structure that can be more general than either martingale or strong mixing".  --- This is very sweet.  The dependence measure they use is, I think, the same as the "gamma' dependence coefficient of Dedecker et al., from their recent book _Weak Dependence_, though apparently independent here.
]]></description>
<dc:subject>statistics learning_theory weak_dependence via:shivak re:your_favorite_dsge_sucks have_read re:XV_for_mixing jiang.wenxin deviation_inequalities</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:24b4bbf591a5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:weak_dependence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:shivak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jiang.wenxin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0811.1629">
    <title>[0811.1629] Stability Bound for Stationary Phi-mixing and Beta-mixing Processes</title>
    <dc:date>2009-04-03T18:56:34+00:00</dc:date>
    <link>http://arxiv.org/abs/0811.1629</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>machine_learning statistics learning_theory ergodic_theory stability_of_learning have_read re:your_favorite_dsge_sucks re:XV_for_mixing re:stacs re:AoS_project</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:445572a82339/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:stacs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0903.1721">
    <title>[0903.1721] A penalized exponential risk bound in parametric estimation</title>
    <dc:date>2009-03-16T18:49:25+00:00</dc:date>
    <link>http://arxiv.org/abs/0903.1721</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to_read statistics learning_theory re:XV_for_mixing re:XV_for_networks</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ba2599dbecb5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.math.lsa.umich.edu/~barvinok/total710.pdf">
    <title>Measure Concentration (Math 710 at UMich)</title>
    <dc:date>2009-02-18T12:15:16+00:00</dc:date>
    <link>http://www.math.lsa.umich.edu/~barvinok/total710.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>probability large_deviations to_read via:shivak concentration_of_measure re:XV_for_mixing barvinok.alexander mathematics</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:963161f1c3af/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:shivak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:barvinok.alexander"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mathematics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://cbcl.mit.edu/projects/cbcl/publications/ps/mukherjee-ACM-06.pdf">
    <title>Stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization</title>
    <dc:date>2009-02-10T13:17:31+00:00</dc:date>
    <link>http://cbcl.mit.edu/projects/cbcl/publications/ps/mukherjee-ACM-06.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Why hadn't I seen this before?
]]></description>
<dc:subject>learning_theory machine_learning cross-validation re:XV_for_networks via:shivak re:XV_for_mixing re:your_favorite_dsge_sucks niyogi.partha</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2e31f1e29ed7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:shivak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_dsge_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:niyogi.partha"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.springerlink.com/content/e00283104305r8g5/">
    <title>Sharp Error Terms for Return Time Statistics under Mixing Conditions</title>
    <dc:date>2009-01-22T15:10:54+00:00</dc:date>
    <link>http://www.springerlink.com/content/e00283104305r8g5/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Pre-print: http://arxiv.org/abs/0812.1016]]></description>
<dc:subject>recurrence_times waiting_times stochastic_processes ergodic_theory to_read re:AoS_project re:XV_for_mixing in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f028390b6c29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:recurrence_times"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:waiting_times"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0806.2941">
    <title>[0806.2941] New Techniques for Empirical Process of Dependent Data</title>
    <dc:date>2008-12-18T19:04:36+00:00</dc:date>
    <link>http://arxiv.org/abs/0806.2941</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>ergodic_theory empirical_processes stochastic_processes to_read re:almost_none re:XV_for_mixing</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:31444c3fc098/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:XV_for_mixing"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>