English

Frank-Wolfe Algorithms for Saddle Point Problems

Optimization and Control 2017-03-07 v3 Machine Learning Machine Learning

Abstract

We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear minimization oracles. Leveraging recent advances in FW optimization, we provide the first proof of convergence of a FW-type saddle point solver over polytopes, thereby partially answering a 30 year-old conjecture. We also survey other convergence results and highlight gaps in the theoretical underpinnings of FW-style algorithms. Motivating applications without known efficient alternatives are explored through structured prediction with combinatorial penalties as well as games over matching polytopes involving an exponential number of constraints.

Keywords

Cite

@article{arxiv.1610.07797,
  title  = {Frank-Wolfe Algorithms for Saddle Point Problems},
  author = {Gauthier Gidel and Tony Jebara and Simon Lacoste-Julien},
  journal= {arXiv preprint arXiv:1610.07797},
  year   = {2017}
}

Comments

Appears in: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017). 39 pages

R2 v1 2026-06-22T16:30:43.312Z