Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Haoning, Qi, Houduo, Zhang, Liping
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909814488039424
author Wang, Haoning
Qi, Houduo
Zhang, Liping
author_facet Wang, Haoning
Qi, Houduo
Zhang, Liping
contents We investigate variants of the Frank-Wolfe (FW) algorithm for smoothing and strongly convex optimization over polyhedral sets, with the goal of designing algorithms that achieve linear convergence while minimizing per-iteration complexity as much as possible. Starting from the simple yet fundamental unit simplex, and based on geometrically intuitive motivations, we introduce a novel oracle called Simplex Linear Minimization Oracle (SLMO), which can be implemented with the same complexity as the standard FW oracle. We then present two FW variants based on SLMO: Simplex Frank-Wolfe and the refined Simplex Frank-Wolfe (rSFW). Both variants achieve a linear convergence rate for all three common step-size rules. Finally, we generalize the entire framework from the unit simplex to arbitrary polytopes. Furthermore, the refinement step in rSFW can accommodate any existing FW strategies such as the well-known away-step and pairwise-step, leading to outstanding numerical performance. We emphasize that the oracle used in our rSFW method requires only one more vector addition compared to the standard LMO, resulting in the lowest per-iteration computational overhead among all known Frank-Wolfe variants with linear convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes
Wang, Haoning
Qi, Houduo
Zhang, Liping
Optimization and Control
90C06, 90C25, 65K05
We investigate variants of the Frank-Wolfe (FW) algorithm for smoothing and strongly convex optimization over polyhedral sets, with the goal of designing algorithms that achieve linear convergence while minimizing per-iteration complexity as much as possible. Starting from the simple yet fundamental unit simplex, and based on geometrically intuitive motivations, we introduce a novel oracle called Simplex Linear Minimization Oracle (SLMO), which can be implemented with the same complexity as the standard FW oracle. We then present two FW variants based on SLMO: Simplex Frank-Wolfe and the refined Simplex Frank-Wolfe (rSFW). Both variants achieve a linear convergence rate for all three common step-size rules. Finally, we generalize the entire framework from the unit simplex to arbitrary polytopes. Furthermore, the refinement step in rSFW can accommodate any existing FW strategies such as the well-known away-step and pairwise-step, leading to outstanding numerical performance. We emphasize that the oracle used in our rSFW method requires only one more vector addition compared to the standard LMO, resulting in the lowest per-iteration computational overhead among all known Frank-Wolfe variants with linear convergence.
title Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes
topic Optimization and Control
90C06, 90C25, 65K05
url https://arxiv.org/abs/2509.24279