Saved in:
Bibliographic Details
Main Authors: Vyguzov, A. A., Stonyakin, F. S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.16468
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916029622386688
author Vyguzov, A. A.
Stonyakin, F. S.
author_facet Vyguzov, A. A.
Stonyakin, F. S.
contents We propose a new version of the Frank-Wolfe method, called the (L0, L1)-Frank-Wolfe algorithm, developed for optimization problems with (L0, L1)-smooth objectives. We establish that this algorithm achieves superior theoretical convergence rates compared to the classical Frank-Wolfe method. In addition, we introduce a novel adaptive procedure, termed the Adaptive (L0, L1)-Frank-Wolfe algorithm, which dynamically adjusts the smoothness parameters to further improve performance and stability. Comprehensive numerical experiments confirm the theoretical results and demonstrate the clear practical advantages of both proposed algorithms over existing Frank-Wolfe variants.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frank-Wolfe Algorithms for (L0, L1)-smooth functions
Vyguzov, A. A.
Stonyakin, F. S.
Optimization and Control
We propose a new version of the Frank-Wolfe method, called the (L0, L1)-Frank-Wolfe algorithm, developed for optimization problems with (L0, L1)-smooth objectives. We establish that this algorithm achieves superior theoretical convergence rates compared to the classical Frank-Wolfe method. In addition, we introduce a novel adaptive procedure, termed the Adaptive (L0, L1)-Frank-Wolfe algorithm, which dynamically adjusts the smoothness parameters to further improve performance and stability. Comprehensive numerical experiments confirm the theoretical results and demonstrate the clear practical advantages of both proposed algorithms over existing Frank-Wolfe variants.
title Frank-Wolfe Algorithms for (L0, L1)-smooth functions
topic Optimization and Control
url https://arxiv.org/abs/2510.16468