题目：Large-Scale Distributed Optimization via ADMM: Algorithms and Applications 时间：6月20日（周一）下午15:00 地点：信电楼117报告厅 报告人：Prof. Tsung-Hui Chang, The Chinese University of Hong Kong, Shenzhen

Abstract: Multi-agent distributed optimization has drawn significant attention in recent years due to the need for large-scale signal processing and machine learning tasks over networks. Distributed optimization methods are appealing as it is not always efficient to pool all the local information for centralized computation, due to large size of problem dimension, a large amount of local data, energy constraints and privacy issues. This talk considers distributed consensus optimization methods based on the alternating direction method of multipliers (ADMM). Specifically, we present a consensus ADMM (C-ADMM) method and a dual consensus ADMM (DC-ADMM) method, which respectively can solve two convex optimization problems in a fully distributed and parallel manner. We will illustrate how the two methods can be applied to solve large-scale machine learning problems and energy management problems in smart grid. Extensions to low-complexity inexact updates and to randomized asynchronous networks will also be presented.

Biography: Tsung-Hui Chang received the B.S. degree in electrical engineering and the Ph.D. degree in communications engineering from the National Tsing Hua University (NTHU), Hsinchu, Taiwan, in 2003 and 2008, respectively. He is currently an Assistant Professor with the School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China. From 2012 to 2015, he was an Assistant Professor with the Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology (NTUST), Taipei, Taiwan. Prior to being a faculty member, Dr. Chang held research positions with NTHU, from 2008 to 2011, and the University of California, Davis, CA, USA, from 2011 to 2012.

Dr. Chang received the Young Scholar Research Award of NTUST in 2014, IEEE ComSoc Asian-Pacific Outstanding Young Researcher Award in 2015, and The Thousand Youth Talent Program of China in 2016. He currently serves as an Associate Editor of IEEE TRANSACTIONS ON SIGNAL PROCESSING and IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS.