English

dHPR: A Distributed Halpern Peaceman--Rachford Method for Non-smooth Distributed Optimization Problems

Optimization and Control 2025-11-14 v1 Distributed, Parallel, and Cluster Computing Multiagent Systems

Abstract

This paper introduces the distributed Halpern Peaceman--Rachford (dHPR) method, an efficient algorithm for solving distributed convex composite optimization problems with non-smooth objectives, which achieves a non-ergodic O(1/k)O(1/k) iteration complexity regarding Karush--Kuhn--Tucker residual. By leveraging the symmetric Gauss--Seidel decomposition, the dHPR effectively decouples the linear operators in the objective functions and consensus constraints while maintaining parallelizability and avoiding additional large proximal terms, leading to a decentralized implementation with provably fast convergence. The superior performance of dHPR is demonstrated through comprehensive numerical experiments on distributed LASSO, group LASSO, and L1L_1-regularized logistic regression problems.

Keywords

Cite

@article{arxiv.2511.10069,
  title  = {dHPR: A Distributed Halpern Peaceman--Rachford Method for Non-smooth Distributed Optimization Problems},
  author = {Zhangcheng Feng and Defeng Sun and Yancheng Yuan and Guojun Zhang},
  journal= {arXiv preprint arXiv:2511.10069},
  year   = {2025}
}
R2 v1 2026-07-01T07:35:16.265Z