Large deviations for empirical entropies of Gibbsian sources

Abstract

The entropy of an ergodic finite-alphabet process can be computed from a single typical sample path x_1^n using the entropy of the k-block empirical probability and letting k grow with $n$ roughly like log n. We further assume that the distribution of the process is a g-measure; g-measures form a large class of Gibbs measures. We prove large deviation principles for conditional, non-conditional and relative k(n)-block empirical entropies.

19 pages; revised version; to appear in Nonlinearity

References in corpus (2)

• Entropy estimation of symbol sequences
• Fluctuations of the Empirical Entropies of a Chain of Infinite Order

Cited by in corpus (4)

• A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures
• Concentration bounds for entropy estimation of one-dimensional Gibbs measures
• Large deviations of return times and related entropy estimators on shift spaces
• A functional central limit theorem for regenerative chains