Ziv-Merhav estimation for hidden-Markov processes
Information Theory
2024-10-23 v1 math.IT
Probability
Abstract
We present a proof of strong consistency of a Ziv-Merhav-type estimator of the cross entropy rate for pairs of hidden-Markov processes. Our proof strategy has two novel aspects: the focus on decoupling properties of the laws and the use of tools from the thermodynamic formalism.
Cite
@article{arxiv.2408.08809,
title = {Ziv-Merhav estimation for hidden-Markov processes},
author = {Nicholas Barnfield and Raphaël Grondin and Gaia Pozzoli and Renaud Raquépas},
journal= {arXiv preprint arXiv:2408.08809},
year = {2024}
}
Comments
Short note prepared for the IEEE International Symposium on Information Theory 2024 on a special case of arXiv:2312.02098