Saved in:
Bibliographic Details
Main Authors: Kamatsuka, Akira, Kazama, Koki, Yoshida, Takahiro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.14304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911927576297472
author Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
author_facet Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
contents $H$-mutual information ($H$-MI) is a wide class of information leakage measures, where $H=(η, F)$ is a pair of monotonically increasing function $η$ and a concave function $F$, which is a generalization of Shannon entropy. $H$-MI is defined as the difference between the generalized entropy $H$ and its conditional version, including Shannon mutual information (MI), Arimoto MI of order $α$, $g$-leakage, and expected value of sample information. This study presents a variational characterization of $H$-MI via statistical decision theory. Based on the characterization, we propose an alternating optimization algorithm for computing $H$-capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Variational Characterization of $H$-Mutual Information and its Application to Computing $H$-Capacity
Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
Information Theory
$H$-mutual information ($H$-MI) is a wide class of information leakage measures, where $H=(η, F)$ is a pair of monotonically increasing function $η$ and a concave function $F$, which is a generalization of Shannon entropy. $H$-MI is defined as the difference between the generalized entropy $H$ and its conditional version, including Shannon mutual information (MI), Arimoto MI of order $α$, $g$-leakage, and expected value of sample information. This study presents a variational characterization of $H$-MI via statistical decision theory. Based on the characterization, we propose an alternating optimization algorithm for computing $H$-capacity.
title A Variational Characterization of $H$-Mutual Information and its Application to Computing $H$-Capacity
topic Information Theory
url https://arxiv.org/abs/2406.14304