报告题目：Asynchronous Distributed Gradient Methods for Multi-agent Optimization
报告人：Lihua Xie（Nanyang Technological University, Singapore）
摘要：This talk is focused on distributed optimization problems in which a number of agents are to seek the global optimum of a sum of cost functions through only local information sharing. We are particularly interested in scenarios where agents are operating asynchronously over stochastic networks subject to random failures. Most existing algorithms require coordinated and decaying stepsizes to ensure zero-gap between the estimated value of each agent and the exact optimum, restricting it from asynchronous implementation and resulting in slower convergence results. To deal with this issue, we develop a new asynchronous distributed gradient method (AsynDGM) based on consensus theory. The proposed algorithm not only allows for asynchronous implementation in a completely distributed manner but also, most importantly, is able to seek the exact optimum even with constant stepsizes. We will show that the assumption of boundedness of gradients, which is widely used in the literature, can be dropped by instead imposing the standard Lipschitz continuity condition on gradients. Moreover, we derive an upperbound of stepsize within which AsynDGM can achieve a linear convergence rate for strongly convex functions with Lipschitz gradients.
个人简介：Lihua Xiereceived the B.E. and M.E. degrees in electrical engineering from Nanjing University of Science and Technology in 1983 and 1986, respectively, and the Ph.D. degree in electrical engineering from the University of Newcastle, Australia, in 1992. He was with the Department of Automatic Control, Nanjing University of Science and Technology from 1986 to 1989. Since 1992, he has been with the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, where he is currently a professor and the Director, Delta-NTU Corporate Lab for Cyber-Physical Systems. He served as the Head of Division of Control and Instrumentation from July 2011 to June 2014.
His current research interests include networked control, multi-agent systems, sensor networks, compressive sensing, localization, and unmanned systems. He has authored/co-authored 8 books, over 350 journal papers, and 7 patents. He was listed as a highly cited researcher by Thomson Reuters in 2014-2017. He is currently an Editor-in-Chief of Unmanned Systems and Associate Editor, IEEE Transactions on Network Control Systems. He has served as Editor for IET Book Series in Control and Associate Editor for Automatica, IEEE Transactions on Automatic Control, IEEE Transactions on Control Systems Technology, IEEE Transactions on Circuit and Systems-II, etc. Dr Xie is Fellow of IEEE, Fellow of IFAC, and an elected member of the Board of Governors of IEEE Control System Society (2016-2018)