<?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://journals.aps.org/prl/abstract/10.1103/g1cz-wk1l"/>
	<rdf:li rdf:resource="https://www.pnas.org/doi/10.1073/pnas.2108492118"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1023/B:JOSS.0000033245.43421.14"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11084-016-9494-1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2209.08832"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2505.10175"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2410.18858"/>
	<rdf:li rdf:resource="https://proceedings.mlr.press/v211/guanchun23a.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2408.02360"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/0804.0327"/>
	<rdf:li rdf:resource="http://videolectures.net/cyberstat2012_granada/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2204.11900"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.08119"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.05093"/>
	<rdf:li rdf:resource="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3997258/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.00814"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1604.07707"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.03585"/>
	<rdf:li rdf:resource="http://link.springer.com/article/10.1007%2FBF00532723"/>
	<rdf:li rdf:resource="http://www.lps.ens.fr/~krzakala/LESHOUCHES2013/book.htm"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0903.2962"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1301.4055"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1110.6121"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1207.6736"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1205.1005"/>
	<rdf:li rdf:resource="http://itf.fys.kuleuven.be/~christ/pub/kyotopaper.pdf"/>
	<rdf:li rdf:resource="http://mathaa.epfl.ch/prst/mourrat/ihpin.pdf"/>
	<rdf:li rdf:resource="http://iopscience.iop.org/1742-5468/focus/extra.focus2"/>
	<rdf:li rdf:resource="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5961833"/>
	<rdf:li rdf:resource="http://www.andreas-maurer.eu/TermoConc.pdf"/>
	<rdf:li rdf:resource="http://www.informaworld.com/smpp/content~content=a923305847~db=all~jumptype=rss"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1009.2830"/>
	<rdf:li rdf:resource="http://terrytao.wordpress.com/2010/08/19/lindenstrauss-ngo-smirnov-villani/"/>
	<rdf:li rdf:resource="http://iopscience.iop.org/1751-8121/40/30/F01/"/>
	<rdf:li rdf:resource="http://ti.arc.nasa.gov/tech/dash/intelligent-data-understanding/probcol/"/>
	<rdf:li rdf:resource="http://complementaryslackness.wordpress.com/"/>
	<rdf:li rdf:resource="http://terrytao.wordpress.com/2010/01/07/mean-field-equations/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1001.3122"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0911.3213"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.5460"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.5761"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0908.2556"/>
	<rdf:li rdf:resource="http://homes.esat.kuleuven.be/~jwillems/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0711.1460"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0903.1484"/>
	<rdf:li rdf:resource="http://www.stanford.edu/~montanar/BOOK/book.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0812.4889"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0810.2164"/>
	<rdf:li rdf:resource="http://www.cpt.univ-mrs.fr/dobrushin/list.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0708.0850"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/cs/0702101"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://journals.aps.org/prl/abstract/10.1103/g1cz-wk1l">
    <title>Random Tree Model of Meaningful Memory | Phys. Rev. Lett.</title>
    <dc:date>2026-06-08T17:18:34+00:00</dc:date>
    <link>https://journals.aps.org/prl/abstract/10.1103/g1cz-wk1l</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Traditional studies of memory for meaningful narratives focus on specific stories and their semantic structures but do not address common quantitative features of recall across different narratives. We introduce a statistical ensemble of random trees to represent narratives as hierarchies of key points, where each node is a compressed representation of its descendant leaves, which are the original narrative segments. Recall from this hierarchical representation is constrained by working memory capacity. Our analytical solution aligns with observations from large-scale narrative recall experiments. Specifically, our model explains that (1) average recall length increases sublinearly with narrative length and (2) individuals summarize increasingly longer narrative segments in each recall sentence. Additionally, the theory predicts that for sufficiently long narratives, a universal, scale-invariant limit emerges, where the fraction of a narrative summarized by a single recall sentence follows a distribution independent of narrative length.]]></description>
<dc:subject>papers to-read memory random-structures language statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5718d5c7a886/</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:memory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:random-structures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.pnas.org/doi/10.1073/pnas.2108492118">
    <title>The overlap gap property: A topological barrier to optimizing over random structures | PNAS</title>
    <dc:date>2026-05-13T17:37:50+00:00</dc:date>
    <link>https://www.pnas.org/doi/10.1073/pnas.2108492118</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[The problem of optimizing over random structures emerges in many areas of science and engineering, ranging from statistical physics to machine learning and artificial intelligence. For many such structures, finding optimal solutions by means of fast algorithms is not known and often is believed not to be possible. At the same time, the formal hardness of these problems in the form of the complexity-theoretic NP-hardness is lacking. A new approach for algorithmic intractability in random structures is described in this article, which is based on the topological disconnectivity property of the set of pairwise distances of near-optimal solutions, called the Overlap Gap Property. The article demonstrates how this property 1) emerges in most models known to exhibit an apparent algorithmic hardness; 2) is consistent with the hardness/tractability phase transition for many models analyzed to the day; and, importantly, 3) allows to mathematically rigorously rule out a large class of algorithms as potential contenders, specifically the algorithms that exhibit the input stability (insensitivity).]]></description>
<dc:subject>papers to-read computational-complexity random-structures statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:483a65f6c008/</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:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:random-structures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1023/B:JOSS.0000033245.43421.14">
    <title>Feynman's Ratchet and Pawl | Journal of Statistical Physics | Springer Nature Link</title>
    <dc:date>2026-03-02T01:40:25+00:00</dc:date>
    <link>https://link.springer.com/article/10.1023/B:JOSS.0000033245.43421.14</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[While many papers in the last few years have dealt with various equations euphemistically called “ratchets,” the original Feyman two-temperature setup has been left largely unchallenged. We present here a look at the details of how this famous engine actually generates motion from a temperature difference.]]></description>
<dc:subject>papers to-read thermodynamics statistical-physics stochastic-thermodynamics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:4410250fda4b/</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:thermodynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:stochastic-thermodynamics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11084-016-9494-1">
    <title>The Logic of Life | Discover Life</title>
    <dc:date>2026-01-08T21:32:48+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11084-016-9494-1</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[In this paper we propose a logical connection between the physical and biological worlds, one resting on a broader understanding of the stability concept. We propose that stability manifests two facets - time and energy, and that stability’s time facet, expressed as persistence, is more general than its energy facet. That insight leads to the logical formulation of the Persistence Principle, which describes the general direction of material change in the universe, and which can be stated most simply as: nature seeks persistent forms. Significantly, the principle is found to express itself in two mathematically distinct ways: in the replicative world through Malthusian exponential growth, and in the ‘regular’ physical/chemical world through Boltzmann’s probabilistic considerations. By encompassing both ‘regular’ and replicative worlds, the principle appears to be able to help reconcile two of the major scientific theories of the 19th century – the Second Law of Thermodynamics and Darwin’s theory of evolution – within a single conceptual framework.]]></description>
<dc:subject>papers to-read biology evolution physics thermodynamics statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:2248c2f5d970/</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:biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:evolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:thermodynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2209.08832">
    <title>[2209.08832] From microscopic to macroscopic scale equations: mean field, hydrodynamic and graph limits</title>
    <dc:date>2025-09-25T13:36:29+00:00</dc:date>
    <link>https://arxiv.org/abs/2209.08832</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Considering finite particle systems, we elaborate on various ways to pass to the limit as thenumber of agents tends to infinity, either by mean field limit, deriving the Vlasov equation,or by hydrodynamic or graph limit, obtaining the Euler equation. We provide convergenceestimates. We also show how to pass from Liouville to Vlasov or to Euler by taking adequatemoments. Our results encompass and generalize a number of known results of the this http URL a surprising consequence of our analysis, we show that sufficiently regular solutions of anylinear PDE can be approximated by solutions of systems of N particles, to within 1/ log log(N ). ]]></description>
<dc:subject>papers to-read statistical-physics dynamical-systems interacting-particle-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:b2fd1757e956/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:interacting-particle-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2505.10175">
    <title>[2505.10175] From Combinatorics to Partial Differential Equations</title>
    <dc:date>2025-05-18T00:44:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2505.10175</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[The optimal matching of point clouds in $\mathbb{R}^d$ is a combinatorial problem; applications in statistics motivate to consider random point clouds, like the Poisson point process. There is a crucial dependance on dimension $d$, with $d=2$ being the critical dimension. This is revealed by adopting an analytical perspective, connecting e.\,g.~to Optimal Transportation. These short notes provide an introduction to the subject. The material presented here is based on a series of lectures held at the International Max Planck Research School during the summer semester 2022. Recordings of the lectures are available at this https URL. ]]></description>
<dc:subject>papers to-read optimal-transportation statistical-physics point-processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:671447c40e37/</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:optimal-transportation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:point-processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2410.18858">
    <title>[2410.18858] Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens</title>
    <dc:date>2024-10-28T16:43:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2410.18858</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Current progress in artificial intelligence is centered around so-called large language models that consist of neural networks processing long sequences of high-dimensional vectors called tokens. Statistical physics provides powerful tools to study the functioning of learning with neural networks and has played a recognized role in the development of modern machine learning. The statistical physics approach relies on simplified and analytically tractable models of data. However, simple tractable models for long sequences of high-dimensional tokens are largely underexplored. Inspired by the crucial role models such as the single-layer teacher-student perceptron (aka generalized linear regression) played in the theory of fully connected neural networks, in this paper, we introduce and study the bilinear sequence regression (BSR) as one of the most basic models for sequences of tokens. We note that modern architectures naturally subsume the BSR model due to the skip connections. Building on recent methodological progress, we compute the Bayes-optimal generalization error for the model in the limit of long sequences of high-dimensional tokens, and provide a message-passing algorithm that matches this performance. We quantify the improvement that optimal learning brings with respect to vectorizing the sequence of tokens and learning via simple linear regression. We also unveil surprising properties of the gradient descent algorithms in the BSR model. ]]></description>
<dc:subject>papers to-read large-language-models transformers statistical-learning statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:90829b4cff11/</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:large-language-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:transformers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://proceedings.mlr.press/v211/guanchun23a.html">
    <title>A Dynamical Systems Perspective on Discrete Optimization</title>
    <dc:date>2024-08-22T15:57:20+00:00</dc:date>
    <link>https://proceedings.mlr.press/v211/guanchun23a.html</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[We discuss a dynamical systems perspective on discrete optimization. Departing from the fact that many combinatorial optimization problems can be reformulated as finding low energy spin con- figurations in corresponding Ising models, we derive a penalized rank-two relaxation of the Ising formulation. It turns out that the associated gradient flow dynamics exactly correspond to a type of hardware solvers termed oscillator-based Ising machines. We also analyze the advantage of adding angle penalties by leveraging random rounding techniques. Therefore, our work contributes to a rigorous understanding of oscillator-based Ising machines by drawing connections to the penalty method in constrained optimization and providing a rationale for the introduction of sub-harmonic injection locking. Furthermore, we characterize a class of coupling functions between oscillators, which ensures convergence to discrete solutions. This class of coupling functions avoids explicit penalty terms or rounding schemes, which are prevalent in other formulations. ]]></description>
<dc:subject>papers to-read dynamical-systems optimization statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:e7a2328fbf3e/</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:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2408.02360">
    <title>[2408.02360] Potential Hessian Ascent: The Sherrington-Kirkpatrick Model</title>
    <dc:date>2024-08-08T01:34:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2408.02360</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[We provide the first iterative spectral algorithm to find near-optima of a random quadratic objective over the discrete hypercube. The algorithm is a randomized Hessian ascent in the solid cube, where we modify the objective by subtracting a specific instance-independent potential function [Chen et al., Communications on Pure and Applied Mathematics, 76(7), 2023]. This extends Subag's algorithmic program of Hessian ascent from the sphere [Subag, Communications on Pure and Applied Mathematics, 74(5), 2021] to the more complex geometry of the cube.
Utilizing tools from free probability theory, we construct an approximate projector into the top-eigenspaces of the Hessian with well-behaved diagonal entries, and use it as the covariance matrix for the random increments. With high probability, the empirical distribution of the iterates approximates the solution to the primal version of the Auffinger-Chen SDE [Auffinger et al., Communications in Mathematical Physics, 335, 2015]. We then bound the change to the modified objective function for every iterate via a Taylor expansion whose derivatives are controlled using various Gaussian concentration bounds and smoothness properties of (a semiconcave regularization of) the Fenchel-Legendre dual to the solution of the Parisi PDE.
These results lay the groundwork for demonstrating the (possible) existence of low-degree sum-of-squares certificates over high-entropy step distributions for a relaxed version of the Parisi formula [Open Question 1.8, arXiv:2401.14383]. ]]></description>
<dc:subject>papers to-read statistical-physics optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5ad9867d43a1/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/0804.0327">
    <title>[0804.0327] The large deviation approach to statistical mechanics</title>
    <dc:date>2024-06-17T20:07:30+00:00</dc:date>
    <link>https://arxiv.org/abs/0804.0327</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[The theory of large deviations is concerned with the exponential decay of probabilities of large fluctuations in random systems. These probabilities are important in many fields of study, including statistics, finance, and engineering, as they often yield valuable information about the large fluctuations of a random system around its most probable state or trajectory. In the context of equilibrium statistical mechanics, the theory of large deviations provides exponential-order estimates of probabilities that refine and generalize Einstein's theory of fluctuations. This review explores this and other connections between large deviation theory and statistical mechanics, in an effort to show that the mathematical language of statistical mechanics is the language of large deviation theory. The first part of the review presents the basics of large deviation theory, and works out many of its classical applications related to sums of random variables and Markov processes. The second part goes through many problems and results of statistical mechanics, and shows how these can be formulated and derived within the context of large deviation theory. The problems and results treated cover a wide range of physical systems, including equilibrium many-particle systems, noise-perturbed dynamics, nonequilibrium systems, as well as multifractals, disordered systems, and chaotic systems. This review also covers many fundamental aspects of statistical mechanics, such as the derivation of variational principles characterizing equilibrium and nonequilibrium states, the breaking of the Legendre transform for nonconcave entropies, and the characterization of nonequilibrium fluctuations through fluctuation relations. ]]></description>
<dc:subject>lecture-notes probability statistical-physics large-deviations</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5489da039ab3/</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:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:large-deviations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://videolectures.net/cyberstat2012_granada/">
    <title>Workshop on Statistical Physics of Inference and Control Theory, Granada 2012 - VideoLectures - VideoLectures.NET</title>
    <dc:date>2023-08-09T21:01:56+00:00</dc:date>
    <link>http://videolectures.net/cyberstat2012_granada/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>statistical-physics inference information control-theory learning dynamical-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:030cd6bd49c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2204.11900">
    <title>[2204.11900] Towards a Geometry and Analysis for Bayesian Mechanics</title>
    <dc:date>2022-08-02T16:23:25+00:00</dc:date>
    <link>https://arxiv.org/abs/2204.11900</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[In this paper, a simple case of Bayesian mechanics under the free energy principle is formulated in axiomatic terms. We argue that any dynamical system with constraints on its dynamics necessarily looks as though it is performing inference against these constraints, and that in a non-isolated system, such constraints imply external environmental variables embedding the system. Using aspects of classical dynamical systems theory in statistical mechanics, we show that this inference is equivalent to a gradient ascent on the Shannon entropy functional, recovering an approximate Bayesian inference under a locally ergodic probability measure on the state space. We also use some geometric notions from dynamical systems theory—namely, that the constraints constitute a gauge degree of freedom—to elaborate on how the desire to stay self-organised can be read as a gauge force acting on the system. In doing so, a number of results of independent interest are given. Overall, we provide a related, but alternative, formalism to those driven purely by descriptions of random dynamical systems, and take a further step towards a comprehensive statement of the physics of self-organisation in formal mathematical language. ]]></description>
<dc:subject>papers to-read Bayesian-inference differential-geometry complex-systems adaptive-systems dynamical-systems statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:d21d4b8939d5/</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:Bayesian-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:differential-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:adaptive-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.08119">
    <title>[2203.08119] A Constraint Geometry for Inference and Integration</title>
    <dc:date>2022-08-02T16:11:46+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.08119</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[We use the geometric framework describing gauge theories to enrich our understanding of the principle of maximum entropy, a variational method appearing in statistical inference and the analysis of stochastic dynamical systems. Using the connection on a principal G-bundle, the gradient flows found in the calculus of functional optimisation are grounded in a geometric picture of constraint functions interacting with the dynamics of the probabilistic degrees of freedom of the process. From this, we can describe the point of maximum entropy as parallel transport over the state space. A reinterpretation of splitting results in stochastic dynamical systems is also suggested. Beyond stochastic analysis, we indicate a collection of geometric structures surrounding energy-based inference. ]]></description>
<dc:subject>papers to-read statistical-physics learning differential-geometry physics-of-information variational-principles-everywhere</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:fee2f33e2ffe/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:differential-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:physics-of-information"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:variational-principles-everywhere"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.05093">
    <title>[2203.05093] Sampling from the Sherrington-Kirkpatrick Gibbs measure via algorithmic stochastic localization</title>
    <dc:date>2022-03-16T13:48:15+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.05093</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[We consider the Sherrington-Kirkpatrick model of spin glasses at high-temperature and no external field, and study the problem of sampling from the Gibbs distribution $\mu$ in polynomial time. We prove that, for any inverse temperature $\beta<1/2$, there exists an algorithm with complexity $O(n^2)$ that samples from a distribution $\mu^{alg}$ which is close in normalized Wasserstein distance to $\mu$. Namely, there exists a coupling of $\mu$ and $\mu^{alg}$ such that if $(x,x^{alg})\in\{-1,+1\}^n\times \{-1,+1\}^n$ is a pair drawn from this coupling, then $n^{-1}\mathbb E\{||x-x^{alg}||_2^2\}=o_n(1)$. The best previous results, by Bauerschmidt and Bodineau and by Eldan, Koehler, and Zeitouni, implied efficient algorithms to approximately sample (under a stronger metric) for $\beta<1/4$.
We complement this result with a negative one, by introducing a suitable "stability" property for sampling algorithms, which is verified by many standard techniques. We prove that no stable algorithm can approximately sample for $\beta>1$, even under the normalized Wasserstein metric.
Our sampling method is based on an algorithmic implementation of stochastic localization, which progressively tilts the measure $\mu$ towards a single configuration, together with an approximate message passing algorithm that is used to approximate the mean of the tilted measure. ]]></description>
<dc:subject>papers to-read sampling SDEs statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:3185e1469e7d/</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:sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:SDEs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3997258/">
    <title>The Metastable Brain</title>
    <dc:date>2020-12-23T21:52:49+00:00</dc:date>
    <link>https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3997258/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read neuroscience complex-systems statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a73bafa4e05a/</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:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.00814">
    <title>[1611.00814] Information-theoretic thresholds from the cavity method</title>
    <dc:date>2016-11-04T03:20:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.00814</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Vindicating a sophisticated but non-rigorous physics approach called the cavity method, we establish a formula for the mutual information in statistical inference problems induced by random graphs. This general result implies the conjecture on the information-theoretic threshold in the disassortative stochastic block model [Decelle et al.: Phys. Rev. E (2011)] and allows us to pinpoint the exact condensation phase transition in random constraint satisfaction problems such as random graph coloring, thereby proving a conjecture from [Krzakala et al.: PNAS (2007)]. As a further application we establish the formula for the mutual information in Low-Density Generator Matrix codes as conjectured in [Montanari: IEEE Transactions on Information Theory (2005)]. The proofs provide a conceptual underpinning of the replica symmetric variant of the cavity method, and we expect that the approach will find many future applications.]]></description>
<dc:subject>papers to-read statistical-physics information-theory optimization graphical-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:7682d0661b22/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1604.07707">
    <title>[1604.07707] Ergodicity of PCA: Equivalence between Spatial and Temporal Mixing Conditions</title>
    <dc:date>2016-04-27T03:12:21+00:00</dc:date>
    <link>http://arxiv.org/abs/1604.07707</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[For a general attractive Probabilistic Cellular Automata on S Z d , we prove that the (time-) convergence towards equilibrium of this Markovian parallel dynamics, exponentially fast in the uniform norm, is equivalent to a condition (A). This condition means the exponential decay of the inuence from the boundary for the invariant measures of the system restricted to nite boxes. For a class of reversible PCA dynamics on {--1, +1} Z d , with a naturally associated Gibbsian potential $\varphi$, we prove that a (spatial-) weak mixing condition (WM) for $\varphi$ implies the validity of the assumption (A); thus exponential (time-) ergodicity of these dynamics towards the unique Gibbs measure associated to $\varphi$ holds. On some particular examples we state that exponential ergodicity holds as soon as there is no phase transition.]]></description>
<dc:subject>papers to-read statistical-physics probability cellular-automata</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f2eb3cde3c99/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:cellular-automata"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.03585">
    <title>[1503.03585] Deep Unsupervised Learning using Nonequilibrium Thermodynamics</title>
    <dc:date>2015-12-08T13:38:21+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.03585</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[A central problem in machine learning involves modeling complex data-sets using highly flexible families of probability distributions in which learning, sampling, inference, and evaluation are still analytically or computationally tractable. Here, we develop an approach that simultaneously achieves both flexibility and tractability. The essential idea, inspired by non-equilibrium statistical physics, is to systematically and slowly destroy structure in a data distribution through an iterative forward diffusion process. We then learn a reverse diffusion process that restores structure in data, yielding a highly flexible and tractable generative model of the data. This approach allows us to rapidly learn, sample from, and evaluate probabilities in deep generative models with thousands of layers or time steps, as well as to compute conditional and posterior probabilities under the learned model. We additionally release an open source reference implementation of the algorithm.]]></description>
<dc:subject>papers deep-learning information-theory statistical-physics have-read meh</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:b817112477ae/</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:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:have-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:meh"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://link.springer.com/article/10.1007%2FBF00532723">
    <title>On entropy and information gain in random fields - Springer</title>
    <dc:date>2015-02-08T20:37:21+00:00</dc:date>
    <link>http://link.springer.com/article/10.1007%2FBF00532723</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read information-theory statistical-physics probability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:bb682501fcd3/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.lps.ens.fr/~krzakala/LESHOUCHES2013/book.htm">
    <title>Les Houches Meeting: &quot;Statistical Physics, Optimization, Inference, and Message-Passing Algorithms&quot;</title>
    <dc:date>2015-02-05T17:47:38+00:00</dc:date>
    <link>http://www.lps.ens.fr/~krzakala/LESHOUCHES2013/book.htm</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>lecture-notes statistical-physics graphical-models machine-learning probability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:0d1db232f428/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0903.2962">
    <title>[0903.2962] A symmetric entropy bound on the non-reconstruction regime of Markov chains on Galton-Watson trees</title>
    <dc:date>2014-01-17T12:55:45+00:00</dc:date>
    <link>http://arxiv.org/abs/0903.2962</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[We give a criterion of the form Q(d)c(M)<1 for the non-reconstructability of tree-indexed q-state Markov chains obtained by broadcasting a signal from the root with a given transition matrix M. Here c(M) is an explicit function, which is convex over the set of M's with a given invariant distribution, that is defined in terms of a (q-1)-dimensional variational problem over symmetric entropies. Further Q(d) is the expected number of offspring on the Galton-Watson tree. This result is equivalent to proving the extremality of the free boundary condition-Gibbs measure within the corresponding Gibbs-simplex. Our theorem holds for possibly non-reversible M and its proof is based on a general Recursion Formula for expectations of a symmetrized relative entropy function, which invites their use as a Lyapunov function. 
In the case of the Potts model, the present theorem reproduces earlier results of the authors, with a simplified proof, in the case of the symmetric Ising model (where the argument becomes similar to the approach of Pemantle and Peres) the method produces the correct reconstruction threshold), in the case of the (strongly) asymmetric Ising model where the Kesten-Stigum bound is known to be not sharp the method provides improved numerical bounds.]]></description>
<dc:subject>papers to-read information-theory statistical-physics markov-chains</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:56ee7d45e679/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:markov-chains"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1301.4055">
    <title>[1301.4055] Structure and eigenvalues of heat-bath Markov chains</title>
    <dc:date>2013-12-12T13:20:22+00:00</dc:date>
    <link>http://arxiv.org/abs/1301.4055</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>to-read papers markov-chains MCMC statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:00acecac01c0/</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:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:markov-chains"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:MCMC"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1110.6121">
    <title>[1110.6121] Truly work-like work extraction</title>
    <dc:date>2013-10-22T19:59:49+00:00</dc:date>
    <link>http://arxiv.org/abs/1110.6121</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read information-theory statistical-physics measure-concentration</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:e4fd5d4a17cd/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:measure-concentration"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1207.6736">
    <title>[1207.6736] Information geometry and sufficient statistics</title>
    <dc:date>2012-07-31T02:53:10+00:00</dc:date>
    <link>http://arxiv.org/abs/1207.6736</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Information geometry provides a geometric approach to families of statistical models. The key geometric structures are the Fisher quadratic form and the Amari-Chentsov tensor. In statistics, the notion of sufficient statistic expresses the criterion for passing from one model to another without loss of information. This leads to the question how the geometric structures behave under such sufficient statistics. While this is well studied in the finite sample size case, in the infinite case, we encounter technical problems concerning the appropriate topologies. Here, we introduce notions of parametrized measure models and tensor fields on them that exhibit the right behavior under statistical transformations. Within this framework, we can then handle the topological issues and show that the Fisher metric and the Amari-Chentsov tensor on statistical models in the class of symmetric 2-tensor fields and 3-tensor fields can be uniquely (up to a constant) characterized by their invariance under sufficient statistics, thereby achieving a full generalization of the original result of Chentsov to infinite sample sizes. More generally, we decompose Markov morphisms between parametrized measure models in terms of statistics. In particular, the Cram'er-Rao inequality, a monotonicity result for the Fisher information, naturally follows.]]></description>
<dc:subject>papers to-read information-geometry probability statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:a6e37d16e43c/</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:information-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1205.1005">
    <title>[1205.1005] Some Refinements of Large Deviation Tail Probabilities</title>
    <dc:date>2012-05-07T09:08:29+00:00</dc:date>
    <link>http://arxiv.org/abs/1205.1005</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We study tail probabilities via some Gaussian approximations. Our results make refinements to large deviation theory. The proof builds on classical results by Bahadur and Rao. Binomial distributions and their tail probabilities are discussed in more detail."]]></description>
<dc:subject>papers to-read statistics probability large-deviations measure-concentration statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:812b2b759a33/</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:large-deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:measure-concentration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://itf.fys.kuleuven.be/~christ/pub/kyotopaper.pdf">
    <title>Fluctuations and response out of equilibrium (C. Maes)</title>
    <dc:date>2012-04-27T14:38:54+00:00</dc:date>
    <link>http://itf.fys.kuleuven.be/~christ/pub/kyotopaper.pdf</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We discuss some recently visited positions towards dealing with nonequilibria from the
mathematical point of view of Markov networks."]]></description>
<dc:subject>papers to-read statistical-physics thermodynamics probability information-theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f8814b7fae43/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:thermodynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mathaa.epfl.ch/prst/mourrat/ihpin.pdf">
    <title>&quot;Lectures on logarithmic Sobolev inequalities&quot; (A. Guionnet and B. Zegarlinski)</title>
    <dc:date>2012-02-05T23:57:52+00:00</dc:date>
    <link>http://mathaa.epfl.ch/prst/mourrat/ihpin.pdf</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>mathematics lecture-notes probability analysis statistical-physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mraginsky/b:2b2f30d3b523/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:lecture-notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://iopscience.iop.org/1742-5468/focus/extra.focus2">
    <title>IOPscience::.. Focus issue on Optimization and Inference in Machine Learning and Physics</title>
    <dc:date>2011-08-14T21:50:34+00:00</dc:date>
    <link>http://iopscience.iop.org/1742-5468/focus/extra.focus2</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>to-read machine-learning statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:316e12c1cfb5/</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:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5961833">
    <title>IEEE Xplore - Data Processing Theorems and the Second Law of Thermodynamics</title>
    <dc:date>2011-07-25T22:08:26+00:00</dc:date>
    <link>http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5961833</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers have-read information-theory thermodynamics statistical-physics markov-chains</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5b5d92df1039/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:thermodynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:markov-chains"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.andreas-maurer.eu/TermoConc.pdf">
    <title>Thermodynamics and Concentration</title>
    <dc:date>2011-03-24T00:52:22+00:00</dc:date>
    <link>http://www.andreas-maurer.eu/TermoConc.pdf</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We show that the thermal subadditivity of entropy provides a common basis to derive a strong form of the bounded dierence inequality and related results as well as more recent inequalities applicable to convex Lipschitz functions, random symmetric matrices, shortest travelling sales-men paths and weakly self-bounding functions. We also give two new concentration inequalities."
]]></description>
<dc:subject>papers to-read measure-concentration information-theory probability statistical-physics statistical-learning via:shivak filetype:pdf media:document</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:094dcfd4b5d4/</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:measure-concentration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:via:shivak"/>
	<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://www.informaworld.com/smpp/content~content=a923305847~db=all~jumptype=rss">
    <title>Feedback control and the arrow of time - International Journal of Control</title>
    <dc:date>2010-09-16T14:59:23+00:00</dc:date>
    <link>http://www.informaworld.com/smpp/content~content=a923305847~db=all~jumptype=rss</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read control-theory statistical-physics cybernetics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:d7558b556812/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:cybernetics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1009.2830">
    <title>[1009.2830] On Lossless Approximations, the Fluctuation-Dissipation Theorem, and Limitations of Measurements</title>
    <dc:date>2010-09-16T04:08:46+00:00</dc:date>
    <link>http://arxiv.org/abs/1009.2830</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>to-read control-theory information-theory statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f1e2b0fbeabe/</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:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://terrytao.wordpress.com/2010/08/19/lindenstrauss-ngo-smirnov-villani/">
    <title>Lindenstrauss, Ngo, Smirnov, Villani « What’s new</title>
    <dc:date>2010-08-19T23:37:58+00:00</dc:date>
    <link>http://terrytao.wordpress.com/2010/08/19/lindenstrauss-ngo-smirnov-villani/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Terry Tao discusses the work of the four 2010 Fields medal winners.
]]></description>
<dc:subject>to-read mathematics dynamical-systems statistical-physics ergodic-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:f968d3d1afd0/</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:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:ergodic-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://iopscience.iop.org/1751-8121/40/30/F01/">
    <title>A note on exponential families of distributions</title>
    <dc:date>2010-08-13T03:53:50+00:00</dc:date>
    <link>http://iopscience.iop.org/1751-8121/40/30/F01/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We show that an arbitrary probability distribution can be represented in an exponential form. In physical contexts, this implies that the equilibrium distribution of any classical or quantum dynamical system is expressible in a grand canonical form." Is there anything really new here, though? ETA: No, cf. Barron and Sheu.
]]></description>
<dc:subject>papers have-read meh probability exponential-families statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:8be45b3c09c2/</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:meh"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:exponential-families"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://ti.arc.nasa.gov/tech/dash/intelligent-data-understanding/probcol/">
    <title>Probability Collectives (David H. Wolpert)</title>
    <dc:date>2010-07-23T14:27:42+00:00</dc:date>
    <link>http://ti.arc.nasa.gov/tech/dash/intelligent-data-understanding/probcol/</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We recently proved that game theory and statistical physics are identical when cast in terms of information theory.

We call the associated formalism Probability Collectives (PC). PC opens many new lines of research, and provides new approaches to problems in distributed control and distributed optimization."
]]></description>
<dc:subject>research papers reference control-theory distributed-systems decision-making game-theory statistical-physics optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:50763dc23280/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:distributed-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://complementaryslackness.wordpress.com/">
    <title>Complementary Slackness</title>
    <dc:date>2010-03-20T05:39:46+00:00</dc:date>
    <link>http://complementaryslackness.wordpress.com/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>blogs philosophy-of-science statistical-physics quantum-mechanics probability</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5b78958e9b94/</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:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:quantum-mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://terrytao.wordpress.com/2010/01/07/mean-field-equations/">
    <title>Mean field games « What’s new</title>
    <dc:date>2010-02-16T16:57:39+00:00</dc:date>
    <link>http://terrytao.wordpress.com/2010/01/07/mean-field-equations/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>game-theory decision-making statistical-physics collective-behavior complex-systems multiagent-systems</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:10e4e2d9db03/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:collective-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:multiagent-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1001.3122">
    <title>[1001.3122] Erasure entropies and Gibbs measures</title>
    <dc:date>2010-01-20T01:43:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1001.3122</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Authors: Aernout van Enter, Evgeny Verbitskiy
]]></description>
<dc:subject>to-read papers information-theory graphical-models statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:124de599a551/</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:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:graphical-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0911.3213">
    <title>[0911.3213] Optimum estimation via gradients of partition functions and information measures: a statistical-mechanical perspective</title>
    <dc:date>2009-11-18T01:28:45+00:00</dc:date>
    <link>http://arxiv.org/abs/0911.3213</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Neri Merhav
]]></description>
<dc:subject>papers have-read estimation information-theory statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:12a84f6d5737/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</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/0910.5761">
    <title>[0910.5761] Which graphical models are difficult to learn? (Authors: Jose Bento, Andrea Montanari)</title>
    <dc:date>2009-11-02T23:17:55+00:00</dc:date>
    <link>http://arxiv.org/abs/0910.5761</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA["We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-complexity algorithms systematically fail when the Markov random field develops long-range correlations. More precisely, this phenomenon appears to be related to the Ising model phase transition (although it does not coincide with it)."
]]></description>
<dc:subject>papers to-read graphical-models statistics machine-learning statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:7d05459b2a69/</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:graphical-models"/>
	<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:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0908.2556">
    <title>[0908.2556] A Backward Particle Interpretation of Feynman-Kac Formulae</title>
    <dc:date>2009-08-23T01:20:39+00:00</dc:date>
    <link>http://arxiv.org/abs/0908.2556</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Pierre Del Moral, Arnaud Doucet, Sumeetpal S. Singh
]]></description>
<dc:subject>papers to-read statistics statistical-physics particle-filters</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:d535551ce973/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:particle-filters"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://homes.esat.kuleuven.be/~jwillems/">
    <title>Home page - Jan C. Willems</title>
    <dc:date>2009-08-10T23:31:20+00:00</dc:date>
    <link>http://homes.esat.kuleuven.be/~jwillems/</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>control-theory optimization statistical-physics mathematics people homepages reference research papers lecture-notes</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:8cb4e252d7dc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
	<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:homepages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:reference"/>
	<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:lecture-notes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0711.1460">
    <title>[0711.1460] On the Thermodynamic Temperature of a General Distribution</title>
    <dc:date>2009-03-17T03:09:57+00:00</dc:date>
    <link>http://arxiv.org/abs/0711.1460</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[(by Krishna R. Narayanan, Arun R. Srinivasa) Even though one of the references is B. Roy Frieden's execrable attempt to "derive" physics from Fisher's information, the information theory in this paper is definitely interesting.
]]></description>
<dc:subject>papers have-read statistics statistical-physics information-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:7ae1ce274527/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0903.1484">
    <title>[0903.1484] Physics of the Shannon Limits</title>
    <dc:date>2009-03-10T00:57:58+00:00</dc:date>
    <link>http://arxiv.org/abs/0903.1484</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[Neri Merhav
]]></description>
<dc:subject>papers have-read statistical-physics information-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:6b386b89de43/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
</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://arxiv.org/abs/0812.4889">
    <title>[0812.4889] Statistical Physics of Signal Estimation in Gaussian Noise: Theory and Examples of Phase Transitions</title>
    <dc:date>2009-01-02T03:40:17+00:00</dc:date>
    <link>http://arxiv.org/abs/0812.4889</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[by Neri Merhav, Dongning Guo, Shlomo Shamai
]]></description>
<dc:subject>papers have-read statistical-physics information-theory</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:5a1be63e726d/</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:statistical-physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0810.2164">
    <title>[0810.2164] Joint source-channel coding via statistical mechanics: thermal equilibrium between the source and the channel</title>
    <dc:date>2008-12-16T01:05:05+00:00</dc:date>
    <link>http://arxiv.org/abs/0810.2164</link>
    <dc:creator>mraginsky</dc:creator><description><![CDATA[by Neri Merhav
]]></description>
<dc:subject>papers to-read information-theory statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:67ef3142c6ba/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cpt.univ-mrs.fr/dobrushin/list.html">
    <title>R.L. Dobrushin. List of papers.</title>
    <dc:date>2008-12-16T00:55:48+00:00</dc:date>
    <link>http://www.cpt.univ-mrs.fr/dobrushin/list.html</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers mathematics probability statistical-physics information-theory reference people</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:02734aedcc72/</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:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:probability"/>
	<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:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:people"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0708.0850">
    <title>[0708.0850] Relations between random coding exponents and the statistical physics of random codes</title>
    <dc:date>2008-07-07T20:47:02+00:00</dc:date>
    <link>http://arxiv.org/abs/0708.0850</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers to-read information-theory statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:2b866ee6aa1f/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/cs/0702101">
    <title>[cs/0702101] An identity of Chernoff bounds with an interpretation in statistical physics and applications in information theory</title>
    <dc:date>2008-07-07T20:45:09+00:00</dc:date>
    <link>http://arxiv.org/abs/cs/0702101</link>
    <dc:creator>mraginsky</dc:creator><dc:subject>papers have-read information-theory statistical-physics</dc:subject>
<dc:identifier>https://pinboard.in/u:mraginsky/b:63bff7f92a12/</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:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mraginsky/t:statistical-physics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>