Refinements of Pinsker's inequality

Authors:
A. A. Fedotov;P. Harremoes;F. Topsoe
Affiliations:
Dept. of Inf. Technol., Inst. of Computational Technol., Novosibirsk, Russia;-;-
Venue:
IEEE Transactions on Information Theory
Year:
2006

Citing 0
Cited 8

Mutual information, variation, and Fano's inequality

Problems of Information Transmission
Universal Estimation of Information Measures for Analog Sources

Foundations and Trends in Communications and Information Theory
Mutual information of several random variables and its estimation via variation

Problems of Information Transmission
Thinning, entropy, and the law of thin numbers

IEEE Transactions on Information Theory
On Pinsker's and Vajda's type inequalities for Csiszár's f-divergences

IEEE Transactions on Information Theory
Information, Divergence and Risk for Binary Experiments

The Journal of Machine Learning Research
Fano type quantum inequalities in terms of q-entropies

Quantum Information Processing
Review: Divergence measures for statistical data processing-An annotated bibliography

Signal Processing

Quantified Score

Hi-index	754.96

Visualization

Abstract

Let V and D denote, respectively, total variation and divergence. We study lower bounds of D with V fixed. The theoretically best (i.e., largest) lower bound determines a function L=L(V), Vajda's (1970) tight lower bound. The main result is an exact parametrization of L. This leads to Taylor polynomials which are lower bounds for L, and thereby to extensions of the classical Pinsker (1960) inequality which has numerous applications, cf. Pinsker and followers.