2021/06/15 by Hadi Reisizadeh, Reisizadeh, Hadi, Behrouz Touri +3
Computer Science · #Cooperative Communication and Network Coding #Distributed Control Multi-Agent Systems #FOS: Mathematics #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
paper · pdf · doi:10.48550/arxiv.2106.08469
openalex publication_date 2021/06/15 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
We study strongly convex distributed optimization problems where a set of agents are interested in solving a separable optimization problem collaboratively. In this paper, we propose and study a two time-scale decentralized gradient descent algorithm for a broad class of lossy sharing of information over time-varying graphs. One time-scale fades out the (lossy) incoming information from neighboring agents, and one time-scale regulates the local loss functions' gradients. For strongly convex loss functions, with a proper choice of step-sizes, we show that the agents' estimates converge to the global optimal state at a rate of O(T-1/2). Another important contribution of this work is to provide novel tools to deal with diminishing average weights over time-varying graphs.