DISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization
Abstract
In this paper, we propose a novel Dual Inexact Splitting Algorithm (DISA) for distributed convex composite optimization problems, where the local loss function consists of a smooth term and a possibly nonsmooth term composed with a linear mapping. DISA, for the first time, eliminates the dependence of the convergent step-size range on the Euclidean norm of the linear mapping, while inheriting the advantages of the classic Primal-Dual Proximal Splitting Algorithm (PD-PSA): simple structure and easy implementation. This indicates that DISA can be executed without prior knowledge of the norm, and tiny step-sizes can be avoided when the norm is large. Additionally, we prove sublinear and linear convergence rates of DISA under general convexity and metric subregularity, respectively. Moreover, we provide a variant of DISA with approximate proximal mapping and prove its global convergence and sublinear convergence rate. Numerical experiments corroborate our theoretical analyses and demonstrate a significant acceleration of DISA compared to existing PD-PSAs.
Cite
@article{arxiv.2209.01850,
title = {DISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization},
author = {Luyao Guo and Xinli Shi and Shaofu Yang and Jinde Cao},
journal= {arXiv preprint arXiv:2209.01850},
year = {2023}
}