Multi-agent constrained optimization of a strongly convex function over time-varying directed networks
Multi-agent constrained optimization of a strongly convex function over time-varying directed networks
复制标题
DOI：
10.1109/allerton.2017.8262781
复制
发表时间：
2017-06
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
我们考虑了无向和有向时变通信网络上的协作多智能体共识优化问题，其中只允许本地通信。目标是最小化特定于智能体的可能非光滑的复合凸函数在特定于智能体的私有圆锥约束集上的总和；因此，最优共识决策应该位于这些私有集合的交叉点。假设和函数是强凸的，给出了在次优性、不可行性和违背一致性情况下的收敛速率；检验底层网络拓扑对所提出的分散算法收敛速度的影响。
We consider cooperative multi-agent consensus optimization problems over undirected and directed time-varying communication networks, where only local communications are allowed. The objective is to minimize the sum of agent-specific possibly non-smooth composite convex functions over agent-specific private conic constraint sets; hence, the optimal consensus decision should lie in the intersection of these private sets. Assuming the sum function is strongly convex, 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 algorithm.