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. 1910.14380
59
30

A Decentralized Proximal Point-type Method for Saddle Point Problems

31 October 2019
Weijie Liu
Aryan Mokhtari
Asuman Ozdaglar
S. Pattathil
Zebang Shen
Nenggan Zheng
ArXivPDFHTML
Abstract

In this paper, we focus on solving a class of constrained non-convex non-concave saddle point problems in a decentralized manner by a group of nodes in a network. Specifically, we assume that each node has access to a summand of a global objective function and nodes are allowed to exchange information only with their neighboring nodes. We propose a decentralized variant of the proximal point method for solving this problem. We show that when the objective function is ρ\rhoρ-weakly convex-weakly concave the iterates converge to approximate stationarity with a rate of O(1/T)\mathcal{O}(1/\sqrt{T})O(1/T​) where the approximation error depends linearly on ρ\sqrt{\rho}ρ​. We further show that when the objective function satisfies the Minty VI condition (which generalizes the convex-concave case) we obtain convergence to stationarity with a rate of O(1/T)\mathcal{O}(1/\sqrt{T})O(1/T​). To the best of our knowledge, our proposed method is the first decentralized algorithm with theoretical guarantees for solving a non-convex non-concave decentralized saddle point problem. Our numerical results for training a general adversarial network (GAN) in a decentralized manner match our theoretical guarantees.

View on arXiv
Comments on this paper