<?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 (mraginsky)</title>
    <link>https://pinboard.in/u:mraginsky/public/</link>
    <description>recent bookmarks from mraginsky</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://jax-ml.github.io/scaling-book/"/>
	<rdf:li rdf:resource="https://aeon.co/essays/the-sovereign-individual-and-the-paradox-of-the-digital-age"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2502.12063"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1011.0014"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2401.14029"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.13306"/>
	<rdf:li rdf:resource="https://royalsocietypublishing.org/doi/10.1098/rsif.2012.0869"/>
	<rdf:li rdf:resource="http://bwlewis.github.io/GLM/"/>
	<rdf:li rdf:resource="http://www.blackboxworkshop.org/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1309.5390"/>
	<rdf:li rdf:resource="http://www.cs.cmu.edu/~venkatg/teaching/CStheory-infoage/"/>
	<rdf:li rdf:resource="http://metamarkets.com/2011/machine-learning-in-wonderland/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1106.4739"/>
	<rdf:li rdf:resource="http://hunch.net/?p=1800"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1101.0833"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1010.5511"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1010.4207"/>
	<rdf:li rdf:resource="http://www.springerlink.com/content/t2effgqq0krwx8q3/"/>
	<rdf:li rdf:resource="http://www.cs.washington.edu/homes/guillory/activecost09.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1008.4654"/>
	<rdf:li rdf:resource="http://lccc.eecs.berkeley.edu/"/>
	<rdf:li rdf:resource="http://userweb.cs.utexas.edu/users/EWD/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1004.1586"/>
	<rdf:li rdf:resource="http://lairlab.org/ispace/"/>
	<rdf:li rdf:resource="http://www.eecs.berkeley.edu/~christos/evol/compevol.htm"/>
	<rdf:li rdf:resource="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ss/1177011073"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0911.3357"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.5460"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.2065v1"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.4627"/>
	<rdf:li rdf:resource="http://www.icsi.berkeley.edu/cgi-bin/pubs/browse.pl?groupid=000006"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0909.2194"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0907.3574"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0908.4073"/>
	<rdf:li rdf:resource="http://blog.computationalcomplexity.org/2009/06/kolmogorov-complexity-proof-of-lov.html"/>
	<rdf:li rdf:resource="https://netfiles.uiuc.edu/angelia/www/nedich.html"/>
	<rdf:li rdf:resource="http://www2.isye.gatech.edu/~ashapiro/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0904.4774"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v10/hoefling09a.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0711.2242"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0809.2085"/>
	<rdf:li rdf:resource="http://www.stanford.edu/~montanar/BOOK/book.html"/>
	<rdf:li rdf:resource="http://www.eng.yale.edu/dcsc/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0809.2650"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0712.4273"/>
	<rdf:li rdf:resource="http://www.cs.yale.edu/homes/spielman/SmoothedAnalysis/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0808.2902"/>
	<rdf:li rdf:resource="http://hunch.net/?p=343"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0807.3050"/>
	<rdf:li rdf:resource="http://www.cs.bu.edu/~crovella/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0806.2890"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0803.0924"/>
	<rdf:li rdf:resource="http://web.mit.edu/andoni/www/LSH/"/>
	<rdf:li rdf:resource="http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Computer-Science/6-451Spring-2005/CourseHome/index.htm"/>
	<rdf:li rdf:resource="http://stellar.mit.edu/S/course/18/fa07/18.409/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://jax-ml.github.io/scaling-book/">
    <title>How To Scale Your Model</title>
    <dc:date>2026-04-18T22:14:08+00:00</dc:date>
    <link>https://jax-ml.github.io/scaling-book/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>books ai transformers deep-learning computation GPUs algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:acea80f9cdad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:transformers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:GPUs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://aeon.co/essays/the-sovereign-individual-and-the-paradox-of-the-digital-age">
    <title>The sovereign individual and the paradox of the digital age | Aeon Essays</title>
    <dc:date>2025-08-24T17:44:21+00:00</dc:date>
    <link>https://aeon.co/essays/the-sovereign-individual-and-the-paradox-of-the-digital-age</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>to-read ai algorithms computation economics capital decision-making</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:31de9a14c266/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:capital"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2502.12063">
    <title>[2502.12063] Low-Rank Thinning</title>
    <dc:date>2025-02-21T23:45:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2502.12063</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of uniform subsampling while substantially reducing the number of summary points. However, existing guarantees cover only a restricted range of distributions and kernel-based quality measures and suffer from pessimistic dimension dependence. To address these deficiencies, we introduce a new low-rank analysis of sub-Gaussian thinning that applies to any distribution and any kernel, guaranteeing high-quality compression whenever the kernel or data matrix is approximately low-rank. To demonstrate the broad applicability of the techniques, we design practical sub-Gaussian thinning approaches that improve upon the best known guarantees for approximating attention in transformers, accelerating stochastic gradient training through reordering, and distinguishing distributions in near-linear time. ]]></description>
<dc:subject>papers to-read kernel-methods algorithms machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:bfd59dc0a0c7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:kernel-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1011.0014">
    <title>[1011.0014] Galois Theory of Algorithms</title>
    <dc:date>2024-07-27T22:37:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1011.0014</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Many different programs are the implementation of the same algorithm. The collection of programs can be partitioned into different classes corresponding to the algorithms they implement. This makes the collection of algorithms a quotient of the collection of programs. Similarly, there are many different algorithms that implement the same computable function. The collection of algorithms can be partitioned into different classes corresponding to what computable function they implement. This makes the collection of computable functions into a quotient of the collection of algorithms. Algorithms are intermediate between programs and functions:
Programs $\twoheadrightarrow$ Algorithms $\twoheadrightarrow$ Functions.
\noindent Galois theory investigates the way that a subobject sits inside an object. We investigate how a quotient object sits inside an object. By looking at the Galois group of programs, we study the intermediate types of algorithms possible and the types of structures these algorithms can have. ]]></description>
<dc:subject>papers to-read computation programming-languages algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:553c510d994a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:programming-languages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2401.14029">
    <title>[2401.14029] Towards a Systems Theory of Algorithms</title>
    <dc:date>2024-01-26T03:06:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2401.14029</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Traditionally, numerical algorithms are seen as isolated pieces of code confined to an {\em in silico} existence. However, this perspective is not appropriate for many modern computational approaches in control, learning, or optimization, wherein {\em in vivo} algorithms interact with their environment. Examples of such {\em open} include various real-time optimization-based control strategies, reinforcement learning, decision-making architectures, online optimization, and many more. Further, even {\em closed} algorithms in learning or optimization are increasingly abstracted in block diagrams with interacting dynamic modules and pipelines. In this opinion paper, we state our vision on a to-be-cultivated {\em systems theory of algorithms} and argue in favour of viewing algorithms as open dynamical systems interacting with other algorithms, physical systems, humans, or databases. Remarkably, the manifold tools developed under the umbrella of systems theory also provide valuable insights into this burgeoning paradigm shift and its accompanying challenges in the algorithmic world. We survey various instances where the principles of algorithmic systems theory are being developed and outline pertinent modeling, analysis, and design challenges. ]]></description>
<dc:subject>papers to-read control-theory algorithms computation learning optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:3cf791653c0d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.13306">
    <title>[2012.13306] Majorizing Measures for the Optimizer</title>
    <dc:date>2022-08-02T16:36:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.13306</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[The theory of majorizing measures, extensively developed by Fernique, Talagrand and many others, provides one of the most general frameworks for controlling the behavior of stochastic processes. In particular, it can be applied to derive quantitative bounds on the expected suprema and the degree of continuity of sample paths for many processes.
One of the crowning achievements of the theory is Talagrand's tight alternative characterization of the suprema of Gaussian processes in terms of majorizing measures. The proof of this theorem was difficult, and thus considerable effort was put into the task of developing both shorter and easier to understand proofs. A major reason for this difficulty was considered to be theory of majorizing measures itself, which had the reputation of being opaque and mysterious. As a consequence, most recent treatments of the theory (including by Talagrand himself) have eschewed the use of majorizing measures in favor of a purely combinatorial approach (the generic chaining) where objects based on sequences of partitions provide roughly matching upper and lower bounds on the desired expected supremum.
In this paper, we return to majorizing measures as a primary object of study, and give a viewpoint that we think is natural and clarifying from an optimization perspective.]]></description>
<dc:subject>papers have-read empirical-processes probability algorithms game-theory optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:c6e9efe1e3f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:empirical-processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://royalsocietypublishing.org/doi/10.1098/rsif.2012.0869">
    <title>The algorithmic origins of life | Journal of The Royal Society Interface</title>
    <dc:date>2022-08-02T16:00:01+00:00</dc:date>
    <link>https://royalsocietypublishing.org/doi/10.1098/rsif.2012.0869</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Although it has been notoriously difficult to pin down precisely what is it that makes life so distinctive and remarkable, there is general agreement that its informational aspect is one key property, perhaps the key property. The unique informational narrative of living systems suggests that life may be characterized by context-dependent causal influences, and, in particular, that top-down (or downward) causation—where higher levels influence and constrain the dynamics of lower levels in organizational hierarchies—may be a major contributor to the hierarchal structure of living systems. Here, we propose that the emergence of life may correspond to a physical transition associated with a shift in the causal structure, where information gains direct and context-dependent causal efficacy over the matter in which it is instantiated. Such a transition may be akin to more traditional physical transitions (e.g. thermodynamic phase transitions), with the crucial distinction that determining which phase (non-life or life) a given system is in requires dynamical information and therefore can only be inferred by identifying causal architecture. We discuss some novel research directions based on this hypothesis, including potential measures of such a transition that may be amenable to laboratory study, and how the proposed mechanism corresponds to the onset of the unique mode of (algorithmic) information processing characteristic of living systems.]]></description>
<dc:subject>papers to-read biogenesis information-theory algorithms causality control-theory dynamical-systems cybernetics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:053e8aa6fdff/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:biogenesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:cybernetics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bwlewis.github.io/GLM/">
    <title>GLMs, abridged</title>
    <dc:date>2016-10-28T14:04:44+00:00</dc:date>
    <link>http://bwlewis.github.io/GLM/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>to-read algorithms statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:98cef4eb7ea6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.blackboxworkshop.org/">
    <title>Black Box Learning and Inference</title>
    <dc:date>2016-02-04T05:07:11+00:00</dc:date>
    <link>http://www.blackboxworkshop.org/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>machine-learning optimization algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:c9a88dd88e6f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1309.5390">
    <title>[1309.5390] Information Acquisition with Sensing Robots: Algorithms and Error Bounds</title>
    <dc:date>2013-09-24T02:30:16+00:00</dc:date>
    <link>http://arxiv.org/abs/1309.5390</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read robotics planning decision-making algorithms re:active_feature_selection_project</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:8a71dcbdaac6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:robotics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:re:active_feature_selection_project"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.cmu.edu/~venkatg/teaching/CStheory-infoage/">
    <title>Computer Science Theory for the Information Age, Spring 2012.</title>
    <dc:date>2012-12-19T00:40:46+00:00</dc:date>
    <link>http://www.cs.cmu.edu/~venkatg/teaching/CStheory-infoage/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Includes draft of a book by John Hopcroft and Ravi Kannan that covers high-dimensional geometry (Johnson-Lindenstrauss and all that), SVD, random graphs, Markov chains, algorithms for "big data", etc.]]></description>
<dc:subject>lecture-notes computer-science machine-learning algorithms probability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:3ce38d78f419/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://metamarkets.com/2011/machine-learning-in-wonderland/">
    <title>Why Generic Machine Learning Fails</title>
    <dc:date>2012-03-10T02:17:47+00:00</dc:date>
    <link>http://metamarkets.com/2011/machine-learning-in-wonderland/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>blogs machine-learning online-learning algorithms prediction computation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:e27184963641/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:blogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1106.4739">
    <title>[1106.4739] Nonasymptotic bounds on the estimation error of MCMC algorithms</title>
    <dc:date>2011-06-24T01:04:27+00:00</dc:date>
    <link>http://arxiv.org/abs/1106.4739</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We address the problem of upper bounding the mean square error of MCMC estimators. Our analysis is non-asymptotic. We first establish a general result valid for essentially all ergodic Markov chains encountered in Bayesian computation and a possibly unbounded target function $f.$ The bound is sharp in the sense that the leading term is exactly $\asvar/n$, where $\asvar$ is the CLT asymptotic variance. Next, we proceed to specific assumptions and give explicit computable bounds for geometrically and polynomially ergodic Markov chains. As a corollary we provide results on confidence estimation."
]]></description>
<dc:subject>papers to-read optimization algorithms MCMC machine-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:2a8c18fddf09/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:MCMC"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://hunch.net/?p=1800">
    <title>The End of the Beginning of Active Learning « Machine Learning (Theory)</title>
    <dc:date>2011-04-21T03:04:35+00:00</dc:date>
    <link>http://hunch.net/?p=1800</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>blogs research active-learning learning-theory machine-learning algorithms optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:fe9e3b472e50/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:blogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:active-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1101.0833">
    <title>[1101.0833] Dynamical systems, simulation, abstract computation</title>
    <dc:date>2011-01-06T16:03:57+00:00</dc:date>
    <link>http://arxiv.org/abs/1101.0833</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[""We survey an area of recent development, relating dynamics to theoretical computer science. We discuss the theoretical limits of simulation and computation of interesting quantities in dynamical systems. We will focus on central objects of the theory of dynamics, as invariant measures and invariant sets, showing that even if they can be computed with arbitrary precision in many interesting cases, there exists some cases in which they can not. We also explain how it is possible to compute the speed of convergence of ergodic averages (when the system is known exactly) and how this entails the computation of arbitrarily good approximations of points of the space having typical statistical behaviour (a sort of constructive version of the pointwise ergodic theorem).""
]]></description>
<dc:subject>papers to-read ergodic-theory dynamical-systems complexity computer-science algorithms simulation</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a0efda18694f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:ergodic-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:simulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1010.5511">
    <title>[1010.5511] Efficient Minimization of Decomposable Submodular Functions</title>
    <dc:date>2010-11-30T15:16:08+00:00</dc:date>
    <link>http://arxiv.org/abs/1010.5511</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read submodular-functions convex-programming optimization algorithms machine-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:06439078745a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:submodular-functions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:convex-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1010.4207">
    <title>[1010.4207] Convex Analysis and Optimization with Submodular Functions: a Tutorial (Francis Bach)</title>
    <dc:date>2010-11-17T13:34:13+00:00</dc:date>
    <link>http://arxiv.org/abs/1010.4207</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["Set-functions appear in many areas of computer science and applied mathematics, such as machine learning, computer vision, operations research or electrical networks. Among these set-functions, submodular functions play an important role, similar to convex functions on vector spaces. In this tutorial, the theory of submodular functions is presented, in a self-contained way, with all results shown from first principles. A good knowledge of convex analysis is assumed."
]]></description>
<dc:subject>papers to-read lecture-notes convex-programming optimization machine-learning algorithms submodular-functions</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:fdd7a763e1ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:convex-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:submodular-functions"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.springerlink.com/content/t2effgqq0krwx8q3/">
    <title>S. Rao Kosaraju, Teresa M. Przytycka and Ryan Borgstrom, &quot;On an Optimal Split Tree Problem&quot;</title>
    <dc:date>2010-11-16T23:28:59+00:00</dc:date>
    <link>http://www.springerlink.com/content/t2effgqq0krwx8q3/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read active-learning decision-making algorithms optimization re:active_feature_selection_project</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:d580d6086393/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:active-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:re:active_feature_selection_project"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.washington.edu/homes/guillory/activecost09.pdf">
    <title>A. Guillory, J. Bilmes, &quot;Average-Case Active Learning with Costs&quot;</title>
    <dc:date>2010-11-16T23:25:21+00:00</dc:date>
    <link>http://www.cs.washington.edu/homes/guillory/activecost09.pdf</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read active-learning decision-making algorithms optimization re:active_feature_selection_project filetype:pdf media:document</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a32c249c41f8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:active-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:re:active_feature_selection_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:filetype:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:media:document"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1008.4654">
    <title>[1008.4654] Freezing and Sleeping: Tracking Experts that Learn by Evolving Past Posteriors</title>
    <dc:date>2010-08-30T00:20:59+00:00</dc:date>
    <link>http://arxiv.org/abs/1008.4654</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Hot damn! "... in this paper we re-examine Freund's problem in case the experts have internal structure that enables them to learn. In this case the problem has two possible interpretations: should the experts learn from all data or only from the subsequence on which they are being tracked? The MPP algorithm solves the first case. Our contribution is to generalise MPP to address the second option. The results we obtain apply to any expert structure that can be formalised using (expert) hidden Markov models. Curiously enough, for our interpretation there are \emph{two} natural reference schemes: freezing and sleeping. For each scheme, we provide an efficient prediction strategy and prove the relevant loss bound."
]]></description>
<dc:subject>papers to-read online-learning decision-making machine-learning algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:46c0e21d3026/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lccc.eecs.berkeley.edu/">
    <title>LCCC - NIPS 2010 Workshop on Learning on Cores, Clusters and Clouds</title>
    <dc:date>2010-08-20T16:10:34+00:00</dc:date>
    <link>http://lccc.eecs.berkeley.edu/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>conferences learning-theory distributed-systems optimization machine-learning algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:03024664a095/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:conferences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://userweb.cs.utexas.edu/users/EWD/">
    <title>E.W.Dijkstra Archive: Home page</title>
    <dc:date>2010-07-29T01:58:39+00:00</dc:date>
    <link>http://userweb.cs.utexas.edu/users/EWD/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>algorithms computer-science mathematics people reference software papers logic proto-bloggers</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a82b8cf19273/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:people"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:logic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:proto-bloggers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1004.1586">
    <title>Belief Propagation for Min-cost Network Flow: Convergence and Correctness</title>
    <dc:date>2010-04-12T16:03:56+00:00</dc:date>
    <link>http://arxiv.org/abs/1004.1586</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["...we present a simple modification of the BP algorithm which gives a fully polynomial-time randomized approximation scheme (FPRAS)...This is the first instance where BP is proved to have fully-polynomial running time."
]]></description>
<dc:subject>papers to-read optimization graphical-models algorithms complexity via:shivak</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:88ddf9d20eab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:via:shivak"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lairlab.org/ispace/">
    <title>Reasoning in Reduced Information Spaces</title>
    <dc:date>2010-04-03T17:56:30+00:00</dc:date>
    <link>http://lairlab.org/ispace/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["...a website for research and coordination on Decentralized Techniques for Reasoning in Reduced Information Spaces (ONR 2009 Multi-disciplinary University Research Project)"
]]></description>
<dc:subject>decision-making decentralized-control machine-learning distributed-systems AI algorithms optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:9193757c612a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decentralized-control"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:AI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.eecs.berkeley.edu/~christos/evol/compevol.htm">
    <title>Computational Aspects of Evolution</title>
    <dc:date>2010-01-24T15:23:37+00:00</dc:date>
    <link>http://www.eecs.berkeley.edu/~christos/evol/compevol.htm</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[A course taught by Christos Papadimitriou
]]></description>
<dc:subject>evolution complexity computation computer-science optimization lecture-notes algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:fd9dd4e3aecb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:evolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ss/1177011073">
    <title>Statistical Science</title>
    <dc:date>2009-12-04T05:10:54+00:00</dc:date>
    <link>http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.ss/1177011073</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Issue on Interface of Probability and Algorithms
]]></description>
<dc:subject>papers to-read statistics probability optimization algorithms computer-science complexity</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:32c892ac0d5c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0911.3357">
    <title>[0911.3357] Fundamentals of Large Sensor Networks: Connectivity, Capacity, Clocks and Computation</title>
    <dc:date>2009-11-18T01:28:20+00:00</dc:date>
    <link>http://arxiv.org/abs/0911.3357</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Nikolaos M. Freris, Hemant Kowshik, P. R. Kumar
]]></description>
<dc:subject>papers to-read sensor-networks distributed-systems optimization information-theory algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:1efdbab838ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sensor-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0910.5460">
    <title>[0910.5460] Gibbs Measures and Phase Transitions on Sparse Random Graphs</title>
    <dc:date>2009-11-10T19:44:22+00:00</dc:date>
    <link>http://arxiv.org/abs/0910.5460</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[lecture notes by Amir Dembo, Andrea Montanari
]]></description>
<dc:subject>to-read lecture-notes reference graph-theory graphical-models sparsity statistical-physics algorithms combinatorics optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:c733a73a2acf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0910.2065v1">
    <title>[0910.2065v1] Decentralized Multi-Armed Bandit with Multiple Distributed Players (Keqin Liu, Qing Zhao)</title>
    <dc:date>2009-11-04T14:25:41+00:00</dc:date>
    <link>http://arxiv.org/abs/0910.2065v1</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[From the abstract: "We consider multi-armed bandit with distributed players, where each player independently samples one of N stochastic processes with unknown parameters and accrues reward in each slot without information exchange. Users choosing the same arm collide, and none or only one receives reward depending on the collision model. This problem can be formulated as a decentralized multi-armed bandit problem."
]]></description>
<dc:subject>papers to-read distributed-systems algorithms optimization decision-making decentralized-control control-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:9251a2a86a5a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decentralized-control"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0910.4627">
    <title>[0910.4627] Self-concordant analysis for logistic regression</title>
    <dc:date>2009-10-27T00:46:34+00:00</dc:date>
    <link>http://arxiv.org/abs/0910.4627</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Francis Bach (INRIA Rocquencourt)
]]></description>
<dc:subject>papers have-read statistics learning-theory optimization algorithms convex-programming</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:0ac552c89903/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:convex-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.icsi.berkeley.edu/cgi-bin/pubs/browse.pl?groupid=000006">
    <title>International Computer Science Institute | Publications: 2009</title>
    <dc:date>2009-10-09T02:40:29+00:00</dc:date>
    <link>http://www.icsi.berkeley.edu/cgi-bin/pubs/browse.pl?groupid=000006</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[ICSI tech repots
]]></description>
<dc:subject>papers complexity computer-science computation algorithms AI statistics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f54c33ffdcb7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:AI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0909.2194">
    <title>[0909.2194] Approximate Nearest Neighbor Search through Comparisons</title>
    <dc:date>2009-09-15T00:04:54+00:00</dc:date>
    <link>http://arxiv.org/abs/0909.2194</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Dominique Tschopp, Suhas Diggavi
]]></description>
<dc:subject>papers to-read algorithms rate-distortion nearest-neighbors</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5d061dec793b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:rate-distortion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:nearest-neighbors"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0907.3574">
    <title>[0907.3574] Message Passing Algorithms for Compressed Sensing</title>
    <dc:date>2009-09-11T01:43:00+00:00</dc:date>
    <link>http://arxiv.org/abs/0907.3574</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[David L. Donoho, Arian Maleki, Andrea Montanari
]]></description>
<dc:subject>papers to-read compressed-sensing message-passing algorithms sparsity signal-processing via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:d972e467b3b8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:message-passing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0908.4073">
    <title>[0908.4073] Distributed Averaging via Lifted Markov Chains</title>
    <dc:date>2009-08-28T00:06:58+00:00</dc:date>
    <link>http://arxiv.org/abs/0908.4073</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Kyomin Jung, Devavrat Shah, Jinwoo Shin
]]></description>
<dc:subject>papers to-read distributed-computing algorithms optimization graph-theory information-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:7255cf70ccd7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.computationalcomplexity.org/2009/06/kolmogorov-complexity-proof-of-lov.html">
    <title>Computational Complexity: A Kolmogorov Complexity Proof of the Lovász Local Lemma</title>
    <dc:date>2009-06-06T05:59:48+00:00</dc:date>
    <link>http://blog.computationalcomplexity.org/2009/06/kolmogorov-complexity-proof-of-lov.html</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>information-theory computer-science complexity algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:14ea8042c30c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://netfiles.uiuc.edu/angelia/www/nedich.html">
    <title>Angelia Nedich</title>
    <dc:date>2009-05-14T21:56:03+00:00</dc:date>
    <link>https://netfiles.uiuc.edu/angelia/www/nedich.html</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>people homepages research papers optimization algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:ed577099e8a8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:people"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:homepages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www2.isye.gatech.edu/~ashapiro/">
    <title>Alex Shapiro's Home Page</title>
    <dc:date>2009-05-09T03:17:13+00:00</dc:date>
    <link>http://www2.isye.gatech.edu/~ashapiro/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>people homepages research optimization complexity algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:8ac4545bda4e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:people"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:homepages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0904.4774">
    <title>[0904.4774] Dictionary Identification - Sparse Matrix-Factorisation via $\ell_1$-Minimisation</title>
    <dc:date>2009-05-07T23:04:36+00:00</dc:date>
    <link>http://arxiv.org/abs/0904.4774</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Remi Gribonval, Karin Schnass
]]></description>
<dc:subject>papers to-read machine-learning sparsity algorithms compressed-sensing</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:785e8fbeb3a1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:compressed-sensing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v10/hoefling09a.html">
    <title>Estimation of Sparse Binary Pairwise Markov Networks using Pseudo-likelihoods</title>
    <dc:date>2009-05-05T19:38:57+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v10/hoefling09a.html</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Holger Höfling, Robert Tibshirani; JMLR 10(Apr):883--906, 2009 (via cshalizi)
]]></description>
<dc:subject>papers have-read statistics machine-learning graphical-models optimization algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a99465c7dccb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0711.2242">
    <title>[0711.2242] Group testing with Random Pools: Phase Transitions and Optimal Strategy</title>
    <dc:date>2009-03-08T18:33:08+00:00</dc:date>
    <link>http://arxiv.org/abs/0711.2242</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[M. Mézard, M.Tarzia, C. Toninelli
]]></description>
<dc:subject>papers to-read statistics machine-learning signal-processing algorithms sparsity graph-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:27c397047eb7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graph-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0809.2085">
    <title>[0809.2085] Clustered Multi-Task Learning: A Convex Formulation</title>
    <dc:date>2009-03-02T22:44:35+00:00</dc:date>
    <link>http://arxiv.org/abs/0809.2085</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Laurent Jacob, Francis Bach (INRIA Rocquencourt), Jean-Philippe Vert
]]></description>
<dc:subject>papers have-read machine-learning algorithms optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:86afce63d2cd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.stanford.edu/~montanar/BOOK/book.html">
    <title>http://www.stanford.edu/~montanar/BOOK/book.html</title>
    <dc:date>2009-01-07T00:09:50+00:00</dc:date>
    <link>http://www.stanford.edu/~montanar/BOOK/book.html</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>books statistical-physics information-theory complexity computation algorithms optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:83d825e37db7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.eng.yale.edu/dcsc/">
    <title>Frontiers in Distributed Communication, Sensing and Control</title>
    <dc:date>2008-11-14T04:42:09+00:00</dc:date>
    <link>http://www.eng.yale.edu/dcsc/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Workshop on the Frontiers in Distributed Communication, Sensing and Control, October 31 - November 2, 2008, Yale University
]]></description>
<dc:subject>conferences research information-theory communications complexity algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:c685e4d86111/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:conferences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:communications"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0809.2650">
    <title>[0809.2650] On Verifiable Sufficient Conditions for Sparse Signal Recovery via</title>
    <dc:date>2008-09-17T02:07:57+00:00</dc:date>
    <link>http://arxiv.org/abs/0809.2650</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[by A. Juditsky and A. Nemirovski
]]></description>
<dc:subject>compressed-sensing algorithms papers to-read statistics mathematics sparsity signal-processing</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f7dc34522bb6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:signal-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0712.4273">
    <title>[0712.4273] Online EM Algorithm for Latent Data Models</title>
    <dc:date>2008-08-27T19:06:31+00:00</dc:date>
    <link>http://arxiv.org/abs/0712.4273</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Olivier Cappe and Eric Moulines
]]></description>
<dc:subject>papers have-read machine-learning optimization statistics algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:11811e5494bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.yale.edu/homes/spielman/SmoothedAnalysis/">
    <title>Research Papers on Smoothed Analysis</title>
    <dc:date>2008-08-24T17:28:49+00:00</dc:date>
    <link>http://www.cs.yale.edu/homes/spielman/SmoothedAnalysis/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers research algorithms complexity computer-science reference optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:8ba1a1b86ecf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0808.2902">
    <title>[0808.2902] A History of Markov Chain Monte Carlo--Subjective Recollections from Incomplete Data</title>
    <dc:date>2008-08-22T01:28:49+00:00</dc:date>
    <link>http://arxiv.org/abs/0808.2902</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[by Christian Robert and George Casella
]]></description>
<dc:subject>papers to-read history_of_statistics algorithms interesting machine-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:2ca99a73f20c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:history_of_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://hunch.net/?p=343">
    <title>Machine Learning (Theory) » Compositional Machine Learning Algorithm Design</title>
    <dc:date>2008-07-26T22:34:34+00:00</dc:date>
    <link>http://hunch.net/?p=343</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>AI algorithms machine-learning interesting polemics learning-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:64552e9deef5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:AI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:polemics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0807.3050">
    <title>[0807.3050] Dimensionally Distributed Learning: Models and Algorithm</title>
    <dc:date>2008-07-22T00:08:54+00:00</dc:date>
    <link>http://arxiv.org/abs/0807.3050</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Haipeng Zheng, Sanjeev R. Kulkarni, H. Vincent Poor
]]></description>
<dc:subject>papers to-read machine-learning learning-theory distributed-computing optimization algorithms sensor-networks</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:385be8223d99/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:sensor-networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.bu.edu/~crovella/">
    <title>Professor Mark Crovella - Home Page</title>
    <dc:date>2008-07-02T13:50:16+00:00</dc:date>
    <link>http://www.cs.bu.edu/~crovella/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>algorithms papers people homepages network-data-analysis forensics security</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:0801dedd0743/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:people"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:homepages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:network-data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:forensics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:security"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0806.2890">
    <title>[0806.2890] Learning Graph Matching</title>
    <dc:date>2008-06-20T12:49:05+00:00</dc:date>
    <link>http://arxiv.org/abs/0806.2890</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>algorithms machine-learning graph-theory papers to-read learning-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f2d085ff33b3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0803.0924">
    <title>[0803.0924] What Can We Learn Privately?</title>
    <dc:date>2008-03-09T23:18:45+00:00</dc:date>
    <link>http://arxiv.org/abs/0803.0924</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>algorithms crypto learning-theory computer-science complexity papers to-read machine-learning</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:c5e6a9b2708a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:crypto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://web.mit.edu/andoni/www/LSH/">
    <title>Locality Sensitive Hashing (LSH) Home Page</title>
    <dc:date>2008-02-25T01:30:34+00:00</dc:date>
    <link>http://web.mit.edu/andoni/www/LSH/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>computer-science data-mining compressed-sensing algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f487b30fd220/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Computer-Science/6-451Spring-2005/CourseHome/index.htm">
    <title>MIT OpenCourseWare | Electrical Engineering and Computer Science | 6.451 Principles of Digital Communication II, Spring 2005 | Home</title>
    <dc:date>2007-10-11T19:19:39+00:00</dc:date>
    <link>http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Computer-Science/6-451Spring-2005/CourseHome/index.htm</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>algorithms coding-theory complexity communications information-theory lecture-notes reference signal-processing</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:0f45744b761b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:coding-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:communications"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:signal-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://stellar.mit.edu/S/course/18/fa07/18.409/">
    <title>18.409 Class Home</title>
    <dc:date>2007-10-10T22:04:56+00:00</dc:date>
    <link>http://stellar.mit.edu/S/course/18/fa07/18.409/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>lecture-notes computer-science algorithms</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:01a06232e8fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>