TL;DR该论文提出了一个名为 EXTRA 的分布式算法,该算法使用固定的步长和同步迭代来解决多智能体网络中的共识优化问题,并具有最佳已知的收敛速率和较好的负载平衡。
Abstract
Recently, there have been growing interests in solving consensus optimization
problems in a multi-agent network. In this paper, we develop a decentralized
algorithm for the consensus optimization problem
$$\min\l