Local Pinsker Inequalities via Stein's Discrete Density Approach

DOI10.1109/TIT.2013.2265392MaRDI QIDQ5346375zbMATH OpenFDO

Authors Christophe Ley, Yvik Swan

Publication date 8 June 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1211.3668

Mathematics Subject Classification ID

Measures of information, entropy (94A17)

Abstract: Pinsker's inequality states that the relative entropy $d_{mathrmKL}(X,Y)$ between two random variables $X$ and $Y$ dominates the square of the total variation distance $d_{mathrmTV}(X,Y)$ between $X$ and $Y$. In this paper we introduce generalized Fisher information distances $mathcalJ(X,Y)$ between discrete distributions $X$ and $Y$ and prove that these also dominate the square of the total variation distance. To this end we introduce a general discrete Stein operator for which we prove a useful covariance identity. We illustrate our approach with several examples. Whenever competitor inequalities are available in the literature, the constants in ours are at least as good, and, in several cases, better.

Cited in

(9)

• Characterizations of non-normalized discrete probability distributions and their application in statistics
• Parametric Stein operators and variance bounds
• Stein's method for the beta distribution and the Pólya-Eggenberger urn
• Fixed point characterizations of continuous univariate probability distributions and their applications
• Entropy and the fourth moment phenomenon
• Stein characterizations for linear combinations of gamma random variables
• Approximation results for sums of independent random variables
• On one extreme value problem for entropy and error probability
• BOUNDS ON EXTROPY WITH VARIATIONAL DISTANCE CONSTRAINT

This page was built for publication: Local Pinsker Inequalities via Stein's Discrete Density Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5346375)