Salvato in:
Dettagli Bibliografici
Autori principali: Vyguzov, Alexander, Stonyakin, Fedor
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.12948
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929428388380672
author Vyguzov, Alexander
Stonyakin, Fedor
author_facet Vyguzov, Alexander
Stonyakin, Fedor
contents The paper introduces a new adaptive version of the Frank-Wolfe algorithm for relatively smooth convex functions. It is proposed to use the Bregman divergence other than half the square of the Euclidean norm in the formula for step-size. Algorithm convergence estimates for minimization problems of relatively smooth convex functions with the triangle scaling property are proved. Computational experiments are performed, and conditions are shown in which the obvious advantage of the proposed algorithm over its Euclidean norm analogue is shown. We also found examples of problems for which the proposed variation of the Frank-Wolfe method works better than known accelerated gradient-type methods for relatively smooth convex functions with the triangle scaling property.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12948
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Variant of Frank-Wolfe Method for Relative Smooth Convex Optimization Problems
Vyguzov, Alexander
Stonyakin, Fedor
Optimization and Control
The paper introduces a new adaptive version of the Frank-Wolfe algorithm for relatively smooth convex functions. It is proposed to use the Bregman divergence other than half the square of the Euclidean norm in the formula for step-size. Algorithm convergence estimates for minimization problems of relatively smooth convex functions with the triangle scaling property are proved. Computational experiments are performed, and conditions are shown in which the obvious advantage of the proposed algorithm over its Euclidean norm analogue is shown. We also found examples of problems for which the proposed variation of the Frank-Wolfe method works better than known accelerated gradient-type methods for relatively smooth convex functions with the triangle scaling property.
title Adaptive Variant of Frank-Wolfe Method for Relative Smooth Convex Optimization Problems
topic Optimization and Control
url https://arxiv.org/abs/2405.12948