期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 62, 期 7, 页码 1750-1761出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2014.2304432
关键词
Decentralized consensus optimization; alternating direction method of multipliers (ADMM); linear convergence
资金
- Chinese Scholarship Council [201306340046, 2011634506]
- NSFC [61004137]
- MOF/MIIT/MOST [BB2100100015]
- ARL
- ARO [W911NF-09-1-0383]
- NSF [DMS-0748839, DMS-1317602]
In decentralized consensus optimization, a connected network of agents collaboratively minimize the sum of their local objective functions over a common decision variable, where their information exchange is restricted between the neighbors. To this end, one can first obtain a problem reformulation and then apply the alternating direction method of multipliers (ADMM). The method applies iterative computation at the individual agents and information exchange between the neighbors. This approach has been observed to converge quickly and deemed powerful. This paper establishes its linear convergence rate for the decentralized consensus optimization problem with strongly convex local objective functions. The theoretical convergence rate is explicitly given in terms of the network topology, the properties of local objective functions, and the algorithm parameter. This result is not only a performance guarantee but also a guideline toward accelerating the ADMM convergence.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据