Decentralized Online Optimization With Global Objectives And Local Communication
2015 American Control Conference (ACC)(2015)
摘要
We consider a decentralized online convex optimization problem in a static undirected network of agents, where each agent controls only a coordinate (or a part) of the global decision vector. For such a problem, we propose a decentralized variant of Nesterov's primal-dual algorithm with dual averaging. To mitigate the disagreements on the primal-vector updates, the agents implement a generalization of the local information-exchange dynamics recently proposed by Li and Marden in We show that the regret has sublinear growth of O(root T) with the time horizon T when the stepsize is of the form 1/root T and the objective functions are Lipschitz continuous convex functions with Lipschitz gradients. We prove an analogous bound on the expected regret for the stochastic variant of the algorithm.
更多查看译文
关键词
local communication,decentralized online convex optimization problem,static undirected network,global decision vector,decentralized variant,Nesterov primal-dual algorithm,primal-vector updates,local information-exchange dynamics,objective functions,Lipschitz gradients,Lipschitz-continuous convex functions,stochastic variant,multiagent network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络