Saved in:
Bibliographic Details
Main Authors: Kamatsuka, Akira, Kazama, Koki, Yoshida, Takahiro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.10950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916713241509888
author Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
author_facet Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
contents This study presents alternating optimization (AO) algorithms for computing $α$-mutual information ($α$-MI) and $α$-capacity based on variational characterizations of $α$-MI using a reverse channel. Specifically, we derive several variational characterizations of Sibson, Arimoto, Augustin--Csisz{\' a}r, and Lapidoth--Pfister MI and introduce novel AO algorithms for computing $α$-MI and $α$-capacity; their performances for computing $α$-capacity are also compared. The comparison results show that the AO algorithm based on the Sibson MI's characterization has the fastest convergence speed.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10950
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Alternating Optimization Approach for Computing $α$-Mutual Information and $α$-Capacity
Kamatsuka, Akira
Kazama, Koki
Yoshida, Takahiro
Information Theory
This study presents alternating optimization (AO) algorithms for computing $α$-mutual information ($α$-MI) and $α$-capacity based on variational characterizations of $α$-MI using a reverse channel. Specifically, we derive several variational characterizations of Sibson, Arimoto, Augustin--Csisz{\' a}r, and Lapidoth--Pfister MI and introduce novel AO algorithms for computing $α$-MI and $α$-capacity; their performances for computing $α$-capacity are also compared. The comparison results show that the AO algorithm based on the Sibson MI's characterization has the fastest convergence speed.
title Alternating Optimization Approach for Computing $α$-Mutual Information and $α$-Capacity
topic Information Theory
url https://arxiv.org/abs/2404.10950