English

Revisiting EXTRA for Smooth Distributed Optimization

Numerical Analysis 2020-06-19 v2 Machine Learning Numerical Analysis Optimization and Control

Abstract

EXTRA is a popular method for dencentralized distributed optimization and has broad applications. This paper revisits EXTRA. First, we give a sharp complexity analysis for EXTRA with the improved O((Lμ+11σ2(W))log1ϵ(1σ2(W)))O\left(\left(\frac{L}{\mu}+\frac{1}{1-\sigma_2(W)}\right)\log\frac{1}{\epsilon(1-\sigma_2(W))}\right) communication and computation complexities for μ\mu-strongly convex and LL-smooth problems, where σ2(W)\sigma_2(W) is the second largest singular value of the weight matrix WW. When the strong convexity is absent, we prove the O((Lϵ+11σ2(W))log11σ2(W))O\left(\left(\frac{L}{\epsilon}+\frac{1}{1-\sigma_2(W)}\right)\log\frac{1}{1-\sigma_2(W)}\right) complexities. Then, we use the Catalyst framework to accelerate EXTRA and obtain the O(Lμ(1σ2(W))logLμ(1σ2(W))log1ϵ)O\left(\sqrt{\frac{L}{\mu(1-\sigma_2(W))}}\log\frac{ L}{\mu(1-\sigma_2(W))}\log\frac{1}{\epsilon}\right) communication and computation complexities for strongly convex and smooth problems and the O(Lϵ(1σ2(W))log1ϵ(1σ2(W)))O\left(\sqrt{\frac{L}{\epsilon(1-\sigma_2(W))}}\log\frac{1}{\epsilon(1-\sigma_2(W))}\right) complexities for non-strongly convex ones. Our communication complexities of the accelerated EXTRA are only worse by the factors of (logLμ(1σ2(W)))\left(\log\frac{L}{\mu(1-\sigma_2(W))}\right) and (log1ϵ(1σ2(W)))\left(\log\frac{1}{\epsilon(1-\sigma_2(W))}\right) from the lower complexity bounds for strongly convex and non-strongly convex problems, respectively.

Cite

@article{arxiv.2002.10110,
  title  = {Revisiting EXTRA for Smooth Distributed Optimization},
  author = {Huan Li and Zhouchen Lin},
  journal= {arXiv preprint arXiv:2002.10110},
  year   = {2020}
}
R2 v1 2026-06-23T13:51:17.825Z