Strong Asymptotic Composition Theorems for Mutual Information Measures
Loading...
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers Inc.
Abstract
We characterize the growth of the Sibson and Arimoto mutual informations and α-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. IEEE
Description
Keywords
Convergence, Entropy, Mutual information, Probability distribution, Random variables, Standards, Velocity measurement, Information theory, Probability distributions, Asymptotics, Composition theorem, Mutual information measures, Mutual informations, Probability: distributions