On the Ziv-Merhav theorem beyond Markovianity II: leveraging the thermodynamic formalism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barnfield, Nicholas, Grondin, Raphaël, Pozzoli, Gaia, Raquépas, Renaud
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910380880560128
author Barnfield, Nicholas
Grondin, Raphaël
Pozzoli, Gaia
Raquépas, Renaud
author_facet Barnfield, Nicholas
Grondin, Raphaël
Pozzoli, Gaia
Raquépas, Renaud
contents We prove asymptotic results for a modification of the cross-entropy estimator originally introduced by Ziv and Merhav in the Markovian setting in 1993. Our results concern a more general class of decoupled measures on shift spaces over a finite alphabet and in particular imply strong asymptotic consistency of the modified estimator for all pairs of functions of stationary, irreducible, finite-state Markov chains satisfying a mild decay condition. Our approach is based on the study of a rescaled cumulant-generating function called the cross-entropic pressure, importing to information theory some techniques from the study of large deviations within the thermodynamic formalism.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02098
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Ziv-Merhav theorem beyond Markovianity II: leveraging the thermodynamic formalism
Barnfield, Nicholas
Grondin, Raphaël
Pozzoli, Gaia
Raquépas, Renaud
Probability
Information Theory
Dynamical Systems
94A17, 37M25, 60F15, 37D35
We prove asymptotic results for a modification of the cross-entropy estimator originally introduced by Ziv and Merhav in the Markovian setting in 1993. Our results concern a more general class of decoupled measures on shift spaces over a finite alphabet and in particular imply strong asymptotic consistency of the modified estimator for all pairs of functions of stationary, irreducible, finite-state Markov chains satisfying a mild decay condition. Our approach is based on the study of a rescaled cumulant-generating function called the cross-entropic pressure, importing to information theory some techniques from the study of large deviations within the thermodynamic formalism.
title On the Ziv-Merhav theorem beyond Markovianity II: leveraging the thermodynamic formalism
topic Probability
Information Theory
Dynamical Systems
94A17, 37M25, 60F15, 37D35
url https://arxiv.org/abs/2312.02098