We consider cooperative multi-agent consensus optimization problems over an undirected network of agents, where only those agents connected by an edge can directly communicate. The objective is to minimize the sum of agent-specific composite convex functions over agent-specific private conic constraint sets; hence, the optimal consensus decision should lie in the intersection of these private sets. We provide convergence rates in sub-optimality, infeasibility and consensus violation; examine the effect of underlying network topology on the convergence rates of the proposed decentralized algorithms; and show how to extend these methods to handle time-varying communication networks.
Necdet Serhat Aybat (Penn State University)
Erfan Yazdandoost Hamedani (Penn State University)
More from the Same Authors
2022 Poster: SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems »
Xuan Zhang · Necdet Serhat Aybat · Mert Gurbuzbalaban
2019 Poster: A Universally Optimal Multistage Accelerated Stochastic Gradient Method »
Necdet Serhat Aybat · Alireza Fallah · Mert Gurbuzbalaban · Asuman Ozdaglar