ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2010.11737
41
11

Efficient Projection-Free Algorithms for Saddle Point Problems

21 October 2020
Cheng Chen
Luo Luo
Weinan Zhang
Yong Yu
ArXiv (abs)PDFHTML
Abstract

The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free property leads to more efficient iterations. In this paper, we study projection-free algorithms for convex-strongly-concave saddle point problems with complicated constraints. Our method combines Conditional Gradient Sliding with Mirror-Prox and shows that it only requires O~(1/ϵ)\tilde{O}(1/\sqrt{\epsilon})O~(1/ϵ​) gradient evaluations and O~(1/ϵ2)\tilde{O}(1/\epsilon^2)O~(1/ϵ2) linear optimizations in the batch setting. We also extend our method to the stochastic setting and propose first stochastic projection-free algorithms for saddle point problems. Experimental results demonstrate the effectiveness of our algorithms and verify our theoretical guarantees.

View on arXiv
Comments on this paper