Multi-agent constrained optimization of a strongly convex function
Multi-agent constrained optimization of a strongly convex function
复制标题
DOI：
10.1109/globalsip.2017.8309021
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
E. Y. Hamedani;N. Aybat
中科院分区：
文献类型：
--
作者：
E. Y. Hamedani;N. Aybat
我们考虑合作多智能体共识优化问题的无向网络的代理，只允许本地通信。我们的目标是最小化代理特定的凸函数在代理特定的私人圆锥约束集的总和。当和函数是强凸的时，我们提供了次最优性、不可行性和共识违反的收敛速度;研究了底层网络拓扑结构对所提出的分散算法的收敛速度的影响。
We consider cooperative multi-agent consensus optimization problems over an undirected network of agents, where only local communications are allowed. The objective is to minimize the sum of agent-specific convex functions over agent-specific private conic constraint sets. We provide convergence rates in sub-optimality, infeasibility and consensus violation when the sum function is strongly convex; examine the effect of underlying network topology on the convergence rates of the proposed decentralized algorithm.