Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.12104 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911578705625088 |
|---|---|
| author | Hough, Matthew |
| author_facet | Hough, Matthew |
| contents | We consider the Frank-Wolfe algorithm for solving variational inequalities over compact, convex sets under a monotone $C^1$ operator and vanishing, nonsummable step sizes. We introduce a continuous-time interpolation of the discrete iteration and use tools from dynamical systems theory to analyze its asymptotic behavior. This allows us to derive convergence results for the original discrete algorithm. Consequently, every cluster point of the iterates is a solution of the underlying variational inequality, the distance from the iterates to the solution set converges to zero, and the Frank-Wolfe gap vanishes asymptotically. In the strongly monotone case, the solution is unique and the iterates converge to it. In particular, this proves Hammond's conjecture on the convergence of generalized fictitious play. We also discuss rates of convergence and under what assumptions rates can be shown. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12104 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Convergence of the Frank-Wolfe Algorithm for Monotone Variational Inequalities Hough, Matthew Optimization and Control 47H05, 90C25 We consider the Frank-Wolfe algorithm for solving variational inequalities over compact, convex sets under a monotone $C^1$ operator and vanishing, nonsummable step sizes. We introduce a continuous-time interpolation of the discrete iteration and use tools from dynamical systems theory to analyze its asymptotic behavior. This allows us to derive convergence results for the original discrete algorithm. Consequently, every cluster point of the iterates is a solution of the underlying variational inequality, the distance from the iterates to the solution set converges to zero, and the Frank-Wolfe gap vanishes asymptotically. In the strongly monotone case, the solution is unique and the iterates converge to it. In particular, this proves Hammond's conjecture on the convergence of generalized fictitious play. We also discuss rates of convergence and under what assumptions rates can be shown. |
| title | Convergence of the Frank-Wolfe Algorithm for Monotone Variational Inequalities |
| topic | Optimization and Control 47H05, 90C25 |
| url | https://arxiv.org/abs/2603.12104 |