English

A Decentralized Proximal Point-type Method for Saddle Point Problems

Optimization and Control 2019-11-01 v1 Machine Learning Machine Learning

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\rho-weakly convex-weakly concave the iterates converge to approximate stationarity with a rate of O(1/T)\mathcal{O}(1/\sqrt{T}) where the approximation error depends linearly on ρ\sqrt{\rho}. 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}). 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.

Keywords

Cite

@article{arxiv.1910.14380,
  title  = {A Decentralized Proximal Point-type Method for Saddle Point Problems},
  author = {Weijie Liu and Aryan Mokhtari and Asuman Ozdaglar and Sarath Pattathil and Zebang Shen and Nenggan Zheng},
  journal= {arXiv preprint arXiv:1910.14380},
  year   = {2019}
}

Comments

18 pages

R2 v1 2026-06-23T12:00:39.073Z