Convergence rates of discrete-time stochastic approximation consensus algorithms: Graph-related limit bounds

doi:10.1016/j.sysconle.2017.12.002

CSpace

	Convergence rates of discrete-time stochastic approximation consensus algorithms: Graph-related limit bounds
	Tang, Huaibin 1,2; Li, Tao 3
	2018-02-01
发表期刊	SYSTEMS & CONTROL LETTERS
ISSN	0167-6911
卷号	112 页码:9-17
摘要	In this paper, we study the convergence rates of the discrete-time stochastic approximation consensus algorithms over sensor networks with communication noises under general digraphs. Basic results of stochastic analysis and algebraic graph theory are used to investigate the dynamics of the consensus error, and the mean square and sample path convergence rates of the consensus error are both given in terms of the graph and noise parameters. Especially, calculation methods to estimate the mean square limit bounds are presented under balanced digraphs, and sufficient conditions on the network topology and the step sizes are given to achieve the fast convergence rate. For the sample path limit bounds, estimation methods are also presented under undirected graphs. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Consensus Sensor network Martingale difference sequence Stochastic approximation Convergence rate
DOI	10.1016/j.sysconle.2017.12.002
语种	英语
资助项目	National Natural Science Foundation of China[61522310] ; National Natural Science Foundation of China[61603215] ; China Postdoctoral Science Foundation[2016M601152] ; Young Scholars Program of Shandong University ; Shanghai Rising-Star Program[15QA1402000] ; Shu Guang project of Shanghai Municipal Education Commission ; Shanghai Education Development Foundation[17SG26]
WOS研究方向	Automation & Control Systems ; Operations Research & Management Science
WOS类目	Automation & Control Systems ; Operations Research & Management Science
WOS记录号	WOS:000427213000002
出版者	ELSEVIER SCIENCE BV
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/29848
专题	中国科学院数学与系统科学研究院
通讯作者	Li, Tao
作者单位	1.Shandong Univ, Sch Microelect, Jinan 250100, Shandong, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Key Lab Syst & Control, Beijing 100190, Peoples R China 3.East China Normal Univ, Dept Math, Shanghai Key Lab Pure Math & Math Practice, Shanghai 200241, Peoples R China
推荐引用方式 GB/T 7714	Tang, Huaibin,Li, Tao. Convergence rates of discrete-time stochastic approximation consensus algorithms: Graph-related limit bounds[J]. SYSTEMS & CONTROL LETTERS,2018,112:9-17.
APA	Tang, Huaibin,&Li, Tao.(2018).Convergence rates of discrete-time stochastic approximation consensus algorithms: Graph-related limit bounds.SYSTEMS & CONTROL LETTERS,112,9-17.
MLA	Tang, Huaibin,et al."Convergence rates of discrete-time stochastic approximation consensus algorithms: Graph-related limit bounds".SYSTEMS & CONTROL LETTERS 112(2018):9-17.