English

A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization

Optimization and Control 2024-03-05 v1

Abstract

This paper studies distributed nonconvex optimization problems with stochastic gradients for a multi-agent system, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed information exchange. We propose a distributed stochastic gradient descent (SGD) algorithm, suitable for a general class of compressors. We show that the proposed algorithm achieves the linear speedup convergence rate O(1/nT)\mathcal{O}(1/\sqrt{nT}) for smooth nonconvex functions, where TT and nn are the number of iterations and agents, respectively. If the global cost function additionally satisfies the Polyak--{\L}ojasiewicz condition, the proposed algorithm can linearly converge to a neighborhood of the global optimum, regardless of whether the stochastic gradient is unbiased or not. Numerical experiments are carried out to verify the efficiency of our algorithm.

Keywords

Cite

@article{arxiv.2403.01322,
  title  = {A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization},
  author = {Antai Xie and Xinlei Yi and Xiaofan Wang and Ming Cao and Xiaoqiang Ren},
  journal= {arXiv preprint arXiv:2403.01322},
  year   = {2024}
}
R2 v1 2026-06-28T15:07:16.617Z