Two-timescale EXTRA for Distributed Smooth Non-convex Optimization
Optimization and Control
2025-09-23 v3
Abstract
In this paper, we study distributed optimization with smooth non-convex local objectives. We propose a novel variant of the well-known EXact firsT-ordeR Algorithm (EXTRA), called Two-timescale EXTRA, by introducing two distinct step-sizes. Leveraging the two-timescale strategy, we construct a Lyapunov function and establish the sub-linear convergence of Two-timescale EXTRA to a consensual first-order stationary point. Additionally, we introduce an off-line sequential method for algorithm parameter selection, and the numerical results support the theoretical guarantees.
Cite
@article{arxiv.2411.19483,
title = {Two-timescale EXTRA for Distributed Smooth Non-convex Optimization},
author = {Zeyu Peng and Farhad Farokhi and Ye Pu},
journal= {arXiv preprint arXiv:2411.19483},
year = {2025}
}
Comments
18 pages