Asynchronous Distributed Optimization With Delay-free Parameters

Xuyang Wu

doi:10.1109/TAC.2025.3590953

Asynchronous Distributed Optimization With Delay-free Parameters

2025-07-21

0

PRE

AI

DOI：10.1109/TAC.2025.3590953

Original

Original request for help

Save

Abstract

En 中文

Existing asynchronous distributed optimization algorithms often use diminishing step-sizes that cause slow practical convergence, or use fixed step-sizes that depend on and decrease with an upper bound of the delays. Not only are such delay bounds hard to obtain in advance, but they also tend to be large and rarely attained, resulting in unnecessarily slow convergence. This article develops asynchronous versions of two distributed algorithms, Prox-DGD and DGD-ATC, for solving consensus optimization problems over undirected networks. In contrast to alternatives, our algorithms can converge to the fixed-point set of their synchronous counterparts using step-sizes that are independent of the delays. We establish convergence guarantees for convex and strongly convex problems under both partial and total asynchrony. We also show that the convergence speed of the two asynchronous methods adjusts to the actual level of asynchrony rather than being constrained by the worst-case. Numerical experiments demonstrate a strong practical performance of our asynchronous algorithms.

Keywords:

Asynchronous optimization

decentralized gradient descent (DGD)

delay-free parameters

distributed optimization

Asynchronous Distributed Optimization With Delay-free Parameters

Abstract

Journal

Organization