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. 2202.05812
31
12

Distributed saddle point problems for strongly concave-convex functions

11 February 2022
Muhammad I. Qureshi
U. Khan
ArXivPDFHTML
Abstract

In this paper, we propose GT-GDA, a distributed optimization method to solve saddle point problems of the form: min⁡xmax⁡y{F(x,y):=G(x)+⟨y,P‾x⟩−H(y)}\min_{\mathbf{x}} \max_{\mathbf{y}} \{F(\mathbf{x},\mathbf{y}) :=G(\mathbf{x}) + \langle \mathbf{y}, \overline{P} \mathbf{x} \rangle - H(\mathbf{y})\}minx​maxy​{F(x,y):=G(x)+⟨y,Px⟩−H(y)}, where the functions G(⋅)G(\cdot)G(⋅), H(⋅)H(\cdot)H(⋅), and the the coupling matrix P‾\overline{P}P are distributed over a strongly connected network of nodes. GT-GDA is a first-order method that uses gradient tracking to eliminate the dissimilarity caused by heterogeneous data distribution among the nodes. In the most general form, GT-GDA includes a consensus over the local coupling matrices to achieve the optimal (unique) saddle point, however, at the expense of increased communication. To avoid this, we propose a more efficient variant GT-GDA-Lite that does not incur the additional communication and analyze its convergence in various scenarios. We show that GT-GDA converges linearly to the unique saddle point solution when G(⋅)G(\cdot)G(⋅) is smooth and convex, H(⋅)H(\cdot)H(⋅) is smooth and strongly convex, and the global coupling matrix P‾\overline{P}P has full column rank. We further characterize the regime under which GT-GDA exhibits a network topology-independent convergence behavior. We next show the linear convergence of GT-GDA to an error around the unique saddle point, which goes to zero when the coupling cost ⟨y,P‾x⟩{\langle \mathbf y, \overline{P} \mathbf x \rangle}⟨y,Px⟩ is common to all nodes, or when G(⋅)G(\cdot)G(⋅) and H(⋅)H(\cdot)H(⋅) are quadratic. Numerical experiments illustrate the convergence properties and importance of GT-GDA and GT-GDA-Lite for several applications.

View on arXiv
Comments on this paper