Optimal Hoeffding bounds for discrete reversible Markov chains

Loading...
Thumbnail Image

Date

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We build optimal exponential bounds for the probabilities of large deviations of sums \sum_{k=1}^nf(X_k) where (X_k) is a finite reversible Markov chain and f is an arbitrary bounded function. These bounds depend only on the stationary mean E_πf, the end-points of the support of f, the sample size n and the second largest eigenvalue λof the transition matrix.

Citation

Collections