Strong Asymptotic Composition Theorems for Mutual Information Measures
Information Theory
2021-11-23 v2 math.IT
Abstract
We characterize the growth of the Sibson and Arimoto mutual informations and -maximal leakage, of any order that is at least unity, between a random variable and a growing set of noisy, conditionally independent and identically-distributed observations of the random variable. Each of these measures increases exponentially fast to a limit that is order- and measure-dependent, with an exponent that is order- and measure-independent.
Cite
@article{arxiv.2005.06033,
title = {Strong Asymptotic Composition Theorems for Mutual Information Measures},
author = {Benjamin Wu and Aaron B. Wagner and Ibrahim Issa and G. Edward Suh},
journal= {arXiv preprint arXiv:2005.06033},
year = {2021}
}
Comments
19 pages, 0 figures