On convergence rate of the Shannon entropy rate of ergodic Markov chains via sample-path simulation

초록

This paper analyzes the asymptotic convergence rate of a simple simulation-based computation of the entropy of a given ergodic Markov chain. We show that the estimated Shannon entropy rate from a single finite-horizon sample-path converges to the true entropy exponentially fast in the horizon size of the sample-path. (C) 2006 Elsevier B.V. All rights reserved.

키워드