Saved in:
Bibliographic Details
Main Authors: Huang, Jinrui, Wang, Xueqin, Liu, Dong, Lan, Jingguo, Wu, Runxiong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.05283
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915834782285824
author Huang, Jinrui
Wang, Xueqin
Liu, Dong
Lan, Jingguo
Wu, Runxiong
author_facet Huang, Jinrui
Wang, Xueqin
Liu, Dong
Lan, Jingguo
Wu, Runxiong
contents This paper focuses on decentralized composite optimization over networks without a central coordinator. We propose a novel decentralized symmetric ADMM algorithm that incorporates multiple communication rounds within each iteration, derived from a new constraint formulation that enables information exchange beyond immediate neighbors. While increasing per-iteration communication, our approach significantly reduces the total number of iterations and overall com- munication cost. We further design optimal communication rules that minimize the number of rounds and variables transmitted per iteration. The proposed algorithm is shown to achieve linear convergence under standard and relatively weak assumptions (e.g., metric subregularity). Extensive experiments on regression and classification tasks validate the theoretical results and demonstrate superior performance compared to existing decentralized optimization methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Communication-Efficient Decentralized Optimization via Double-Communication Symmetric ADMM
Huang, Jinrui
Wang, Xueqin
Liu, Dong
Lan, Jingguo
Wu, Runxiong
Optimization and Control
This paper focuses on decentralized composite optimization over networks without a central coordinator. We propose a novel decentralized symmetric ADMM algorithm that incorporates multiple communication rounds within each iteration, derived from a new constraint formulation that enables information exchange beyond immediate neighbors. While increasing per-iteration communication, our approach significantly reduces the total number of iterations and overall com- munication cost. We further design optimal communication rules that minimize the number of rounds and variables transmitted per iteration. The proposed algorithm is shown to achieve linear convergence under standard and relatively weak assumptions (e.g., metric subregularity). Extensive experiments on regression and classification tasks validate the theoretical results and demonstrate superior performance compared to existing decentralized optimization methods.
title Communication-Efficient Decentralized Optimization via Double-Communication Symmetric ADMM
topic Optimization and Control
url https://arxiv.org/abs/2511.05283