A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Baghbadorani, Reza Rahimi, Esfahani, Peyman Mohajerin, Grammatico, Sergio
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914075447918592
author Baghbadorani, Reza Rahimi
Esfahani, Peyman Mohajerin
Grammatico, Sergio
author_facet Baghbadorani, Reza Rahimi
Esfahani, Peyman Mohajerin
Grammatico, Sergio
contents We propose an accelerated algorithm with a Frank-Wolfe method as an oracle for solving strongly monotone variational inequality problems. While standard solution approaches, such as projected gradient descent (aka value iteration), involve projecting onto the desired set at each iteration, a distinctive feature of our proposed method is the use of a linear minimization oracle in each iteration. This difference potentially reduces the projection cost, a factor that can become significant for certain sets or in high-dimensional problems. We validate the performance of the proposed algorithm on the traffic assignment problem, motivated by the fact that the projection complexity per iteration increases exponentially with respect to the number of links.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities
Baghbadorani, Reza Rahimi
Esfahani, Peyman Mohajerin
Grammatico, Sergio
Optimization and Control
We propose an accelerated algorithm with a Frank-Wolfe method as an oracle for solving strongly monotone variational inequality problems. While standard solution approaches, such as projected gradient descent (aka value iteration), involve projecting onto the desired set at each iteration, a distinctive feature of our proposed method is the use of a linear minimization oracle in each iteration. This difference potentially reduces the projection cost, a factor that can become significant for certain sets or in high-dimensional problems. We validate the performance of the proposed algorithm on the traffic assignment problem, motivated by the fact that the projection complexity per iteration increases exponentially with respect to the number of links.
title A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities
topic Optimization and Control
url https://arxiv.org/abs/2510.03842