Bregman proximal gradient method for linear optimization under entropic constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Briceño-Arias, Luis M., Treust, Maël Le
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908996222320640
author Briceño-Arias, Luis M.
Treust, Maël Le
author_facet Briceño-Arias, Luis M.
Treust, Maël Le
contents In this paper, we present an efficient algorithm for solving a linear optimization problem with entropic constraints, a class of problems that arises in game theory and information theory. Our analysis distinguishes between the cases of active and inactive constraints, addressing each using a Bregman proximal gradient method with entropic Legendre functions, for which we establish a convergence rate of $O(1/n)$ in objective values. For a specific cost structure, our framework provides a theoretical justification for the well-known Blahut-Arimoto algorithm and the uniqueness of the Lagrange multiplier associated with the entropic constraint. In the active constraint setting, we include a bisection procedure to approximate the strictly positive Lagrange multiplier. The efficiency of the proposed method is illustrated through comparisons with standard optimization solvers on a representative example from game theory, including extensions to higher-dimensional settings.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bregman proximal gradient method for linear optimization under entropic constraints
Briceño-Arias, Luis M.
Treust, Maël Le
Optimization and Control
90C25 and 65K05
In this paper, we present an efficient algorithm for solving a linear optimization problem with entropic constraints, a class of problems that arises in game theory and information theory. Our analysis distinguishes between the cases of active and inactive constraints, addressing each using a Bregman proximal gradient method with entropic Legendre functions, for which we establish a convergence rate of $O(1/n)$ in objective values. For a specific cost structure, our framework provides a theoretical justification for the well-known Blahut-Arimoto algorithm and the uniqueness of the Lagrange multiplier associated with the entropic constraint. In the active constraint setting, we include a bisection procedure to approximate the strictly positive Lagrange multiplier. The efficiency of the proposed method is illustrated through comparisons with standard optimization solvers on a representative example from game theory, including extensions to higher-dimensional settings.
title Bregman proximal gradient method for linear optimization under entropic constraints
topic Optimization and Control
90C25 and 65K05
url https://arxiv.org/abs/2506.10849