PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Convergence of Markov chains in information divergence
Peter Harremoes and Klaus Holst
Journal of Theoretical Probability Volume 21, pp. 186-202, 2009. ISSN 1572-9230

Abstract

Information theoretic methods are used to prove convergence in information divergence of reversible Markov chains. Also some ergodic theorems for information divergence are proved.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:4994
Deposited By:Peter Harremoes
Deposited On:24 March 2009

[Edit]