Limit theorems for the sample entropy of hidden Markov chains

The Shannon-McMillan-Breiman theorem asserts that the sample entropy of a stationary and ergodic stochastic process converges to the entropy rate of the same process (as the sample size tends to infinity) almost surely. In this paper, we restrict our attention to the convergence behavior of the sample entropy of hidden Markov chains. Under certain positivity assumptions, we prove that a central limit theorem (CLT) with some Berry-Esseen bound for the sample entropy of a hidden Markov chain, and we use this CLT to establish a law of iterated logarithm (LIL) for the sample entropy.