Enregistré dans:
Détails bibliographiques
Auteurs principaux: Millan, R. Diaz, Ferreira, Orizon Pereira, Ugon, Julien
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.17272
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911072762462208
author Millan, R. Diaz
Ferreira, Orizon Pereira
Ugon, Julien
author_facet Millan, R. Diaz
Ferreira, Orizon Pereira
Ugon, Julien
contents We study the Frank-Wolfe algorithm for minimizing a differentiable function with Lipschitz continuous gradient over a compact convex set. To extend classical complexity bounds to certain non-convex functions, we focus on the class of \emph{star-convex functions}, which retain essential geometric properties despite the lack of convexity. We establish iteration-complexity bounds of $\mathcal{O}(1/k)$ for both the objective values and the duality gap under star-convexity, using diminishing, Armijo-type, and Lipschitz-based stepsize rules. Notably, the diminishing and Armijo strategies do not require prior knowledge of Lipschitz or curvature constants. These results demonstrate that the Frank-Wolfe method preserves optimal complexity guarantees beyond the convex setting.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17272
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frank-Wolfe algorithm for star-convex functions
Millan, R. Diaz
Ferreira, Orizon Pereira
Ugon, Julien
Optimization and Control
We study the Frank-Wolfe algorithm for minimizing a differentiable function with Lipschitz continuous gradient over a compact convex set. To extend classical complexity bounds to certain non-convex functions, we focus on the class of \emph{star-convex functions}, which retain essential geometric properties despite the lack of convexity. We establish iteration-complexity bounds of $\mathcal{O}(1/k)$ for both the objective values and the duality gap under star-convexity, using diminishing, Armijo-type, and Lipschitz-based stepsize rules. Notably, the diminishing and Armijo strategies do not require prior knowledge of Lipschitz or curvature constants. These results demonstrate that the Frank-Wolfe method preserves optimal complexity guarantees beyond the convex setting.
title Frank-Wolfe algorithm for star-convex functions
topic Optimization and Control
url https://arxiv.org/abs/2507.17272