A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization
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 for smooth nonconvex functions, where and 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.
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}
}