Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 17, 2025SIAM Journal on OptimizationOpen Access

Generalized Optimistic Methods for Convex-Concave Saddle Point Problems

View Full Paper
Ask AI
Bookmark
Share

Authors

RJRuichen JiangGoogle (United States)AMAryan MokhtariGoogle (United States)

Discussion

Loading...

Member takes

Implication

This new method analyzes saddle point problems, proposing improvements on optimistic methods for efficiency.

Key Points

  • The new generalized optimistic method significantly improves solving convex-concave saddle point problems.
  • The framework achieves a complexity bound of O(ε^(-2/3)) for the primal-dual gap in this setting.
  • A backtracking line search is developed for selecting step sizes without smoothness knowledge.
  • Convergence rates are established regarding tangent residuals, extending metrics to unconstrained cases.

Cite This Study

Jiang et al. (2025) studied this question.

synapsesocial.com/papers/68d45e4e31b076d99fa5e4d4https://doi.org/10.1137/24m1630475
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Forward-Backward Splitting Method for Monotone Inclusions Without Cocoercivity2020 · 244 citations
  2. 2Monotone Operators and the Proximal Point Algorithm1976 · 3,651 citations
  3. 3Iteration-Complexity of a Newton Proximal Extragradient Method for Monotone Variational Inequalities and Inclusion Problems2012 · 47 citations