Concentration of the information in data with log-concave distributions

DOI10.1214/10-AOP592MaRDI QIDQ717889zbMATH OpenOpenAlexFDO

Authors Mokshay Madiman, S. G. Bobkov

Publication date 10 October 2011

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1012.5457

zbMATH Keywords

entropyconcentrationlog-concave distributionsShannon-McMillan-Breiman theoremasymptotic equipartition property

Mathematics Subject Classification ID

Information theory (general) (94A15) General theory of stochastic processes (60G07)

Abstract: A concentration property of the functional $-logf(X)$ is demonstrated, when a random vector X has a log-concave density f on $mathbb{R}^n$. This concentration property implies in particular an extension of the Shannon-McMillan-Breiman strong ergodic theorem to the class of discrete-time stochastic processes with log-concave marginals.

Recommendations

• Optimal concentration of information content for log-concave densities
• Concentration of information content for convex measures
• scientific article; zbMATH DE number 868060
• Information inequalities and concentration of measure
• Concentration functions and entropy bounds for discrete log-concave distributions
• Dimension-free information concentration via exp-concavity
• Concentration inequalities for ultra log-concave distributions
• Intrinsic Entropies of Log-Concave Distributions
• Entropy and information jump for log-concave vectors

Cites work

• scientific article; zbMATH DE number 3905555 (Why is no real title available?)
• scientific article; zbMATH DE number 1975218 (Why is no real title available?)
• scientific article; zbMATH DE number 3205806 (Why is no real title available?)
• A Mathematical Theory of Communication
• A sandwich proof of the Shannon-McMillan-Breiman theorem
• A simple proof of the Moy-Perez generalization of the Shannon-McMillan theorem
• Complements of Lyapunov's inequality
• Convex measures on locally convex spaces
• Correction Notes: Correction to "The Individual Ergodic Theorem of Information Theory"
• Extremal properties of half-spaces for log-concave distributions
• Gaussian feedback capacity
• Generalizations of Shannon-McMillan theorem
• Geometry of log-concave functions and measures
• Isoperimetric problems for convex bodies and a localization lemma
• Moment inequalities of Polya frequency functions
• Properties of Probability Distributions with Monotone Hazard Rate
• Random walks in a convex body and an improved volume algorithm
• The Basic Theorems of Information Theory
• The Entropy Per Coordinate of a Random Vector is Highly Constrained Under Convexity Conditions
• The strong ergodic theorem for densities: Generalized Shannon-McMillan- Breiman theorem

Cited in

(40)

• Preservation of log-concavity under convolution
• Reverse Brunn-Minkowski and reverse entropy power inequalities for convex measures
• Concentration functions and entropy bounds for discrete log-concave distributions
• Chernoff's density is log-concave
• A discrete complement of Lyapunov's inequality and its information theoretic consequences
• Varentropy of order statistics and some stochastic comparisons
• Dimensional behaviour of entropy and information
• Varentropy estimators with applications in testing uniformity
• Geometric and functional inequalities for log-concave probability sequences
• On stochastic properties of past varentropy with applications.
• Maximum-a-posteriori estimation with Bayesian confidence regions
• scientific article; zbMATH DE number 4012483 (Why is no real title available?)
• A NEW GENERALIZED VARENTROPY AND ITS PROPERTIES
• Hyperbolic measures on infinite dimensional spaces
• SOME MEASURES INFORMATION FOR GENERALIZED AND q-GENERALIZED EXTREME VALUES AND ITS PROPERTIES
• Talagrand concentration inequalities for stochastic partial differential equations
• Regularization under diffusion and anticoncentration of the information content
• On the \(s\)-Gaussian measure in \(\mathbb{R}^n\)
• Aging notions, stochastic orders, and expected utilities
• Optimal concentration of information content for log-concave densities
• A note on transportation cost inequalities for diffusions with reflections
• Dimension-free information concentration via exp-concavity
• On the log-concavity of a Jacobi theta function
• ANALYSIS AND APPLICATIONS OF THE RESIDUAL VARENTROPY OF RANDOM LIFETIMES
• Concentration of information content for convex measures
• PRESERVATION OF LOG-CONCAVITY AND LOG-CONVEXITY UNDER OPERATORS
• Stochastic properties of varentropy based on residual lifetime
• A combinatorial approach to small ball inequalities for sums and differences
• Log-concavity and strong log-concavity: a review
• Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. I: Methodology and experiments
• On the exponentially weighted aggregate with the Laplace prior
• Varentropy estimators applied to test of fit for inverse Gaussian distribution
• Varentropy estimators applied to goodness of fit tests for the Gumbel distribution
• Concentration of the intrinsic volumes of a convex body
• Dimensional variance inequalities of Brascamp-Lieb type and a local approach to dimensional Prékopa's theorem
• Varentropy of past lifetimes
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• A multivariate Gnedenko law of large numbers
• A distributed framework for the construction of transport maps
• An ergodic theorem for constrained sequences of functions

This page was built for publication: Concentration of the information in data with log-concave distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q717889)