Convergence of a Distributed Least Squares

doi:10.1109/TAC.2020.3047989

	Convergence of a Distributed Least Squares
	Xie, Siyu 2; Zhang, Yaqi 1,3; Guo, Lei 1,3
刊名	IEEE TRANSACTIONS ON AUTOMATIC CONTROL
	2021-10-01
卷号	66 期号:10 页码:4952-4959
关键词	Convergence Estimation Symmetric matrices Stochastic processes Task analysis Complexity theory Adaptive control Convergence cooperative excitation diffusion strategies distributed estimation least squares (LS) martingale theory regret
ISSN号	0018-9286
DOI	10.1109/TAC.2020.3047989
英文摘要	In this article, we consider a least-squares (LS)-based distributed algorithm build on a sensor network to estimate an unknown parameter vector of a dynamical system, where each sensor in the network has partial information only but is allowed to communicate with its neighbors. Our main task is to generalize the well-known theoretical results on the traditional LS to the current distributed case by establishing both the upper bound of the accumulated regrets of the adaptive predictor and the convergence of the distributed LS estimator, with the following key features compared with the existing literature on distributed estimation: First, our theory does not need the previously imposed independence, stationarity, or Gaussian property on the system signals, and hence is applicable to stochastic systems with feedback. Second, the cooperative excitation condition introduced and used in this article for the convergence of the distributed LS estimate is the weakest possible one, which shows that even if any individual sensor cannot estimate the unknown parameter by the traditional LS, the whole network can still fulfill the estimation task by the distributed LS.
资助项目	National Natural Science Foundation of China[11688101]
WOS研究方向	Automation & Control Systems ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000698859900049
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/59356]
专题	中国科学院数学与系统科学研究院
通讯作者	Guo, Lei
作者单位	1.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China 2.Wayne State Univ, Dept Elect & Comp Engn, Detroit, MI 48202 USA 3.Chinese Acad Sci, Acad Math & Syst Sci, Key Lab Syst & Control, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xie, Siyu,Zhang, Yaqi,Guo, Lei. Convergence of a Distributed Least Squares[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL,2021,66(10):4952-4959.
APA	Xie, Siyu,Zhang, Yaqi,&Guo, Lei.(2021).Convergence of a Distributed Least Squares.IEEE TRANSACTIONS ON AUTOMATIC CONTROL,66(10),4952-4959.
MLA	Xie, Siyu,et al."Convergence of a Distributed Least Squares".IEEE TRANSACTIONS ON AUTOMATIC CONTROL 66.10(2021):4952-4959.