Bounding $\bar{d}$-distance by informational divergence: a method to prove measure concentration
Author:
- K. MartonKMK. Marton
Open Access
- 1 April 1996
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Probability
- Vol. 24 (2) , 857-866
Abstract
There is a simple inequality by Pinsker between variational distance and informational divergence of probability measures defined on arbitrary probability spaces. We shall consider probability measures on sequences taken from countable alphabets, and derive, from Pinsker's inequality, bounds on the $\bar{d}$-distance by informational divergence. Such bounds can be used to prove the "concentration of measure" phenomenon for some nonproduct distributions.Keywords
This publication has 7 references indexed in Scilit:
- A measure concentration inequality for contracting markov chainsGeometric and Functional Analysis, 1996
- Concentration of measure and isoperimetric inequalities in product spacesPublications mathématiques de l'IHÉS, 1995
- The positive-divergence and blowing-up propertiesIsrael Journal of Mathematics, 1994
- Error exponents for distributed detection of Markov sourcesIEEE Transactions on Information Theory, 1994
- On the method of bounded differences1989
- A simple proof of the blowing-up lemma (Corresp.)IEEE Transactions on Information Theory, 1986
- Bounds on conditional probabilities with applications in multi-user communicationProbability Theory and Related Fields, 1976