Concentration of the information in data with log-concave distributions
arXiv:1012.5457 · doi:10.1214/10-AOP592
Abstract
A concentration property of the functional is demonstrated, when a random vector X has a log-concave density f on . 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.
Published in at http://dx.doi.org/10.1214/10-AOP592 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (1)
Cited by in corpus (20)
- Reverse Brunn-Minkowski and reverse entropy power inequalities for convex measures
- Forward and Reverse Entropy Power Inequalities in Convex Geometry
- Optimal Concentration of Information Content For Log-Concave Densities
- Dimensional behaviour of entropy and information
- A Characterization of Guesswork on Swiftly Tilting Curves
- Analysis and applications of the residual varentropy of random lifetimes
- Regularization under diffusion and anti-concentration of the information content
- The Differential Entropy of Mixtures: New Bounds and Applications
- Sharp moment-entropy inequalities and capacity bounds for log-concave distributions
- A multivariate Gnedenko law of large numbers
- Concentration of information content for convex measures
- Further Analysis of Outlier Detection with Deep Generative Models
- A combinatorial approach to small ball inequalities for sums and differences
- On the equivalence of modes of convergence for log-concave measures
- Empirical distribution of good channel codes with non-vanishing error probability (extended version)
- On the Exponentially Weighted Aggregate with the Laplace Prior
- Dimension-free Information Concentration via Exp-Concavity
- Hyperbolic Measures on Infinite Dimensional Spaces
- How Many Queries Will Resolve Common Randomness?
- Mixed integrals and related inequalities