Analysis of Alternating Direction Method of Multipliers for Nonconvex Problems
Abstract
A popular approach to solve large scale optimization problems involving big data is by the Alternating Direction Method of Multipliers (ADMM). The existing convergence analysis of this algorithm is limited mostly to the convex case. In this lecture, the speaker will present some recent work on the analysis of ADMM for the nonconvex case and discuss some open questions.
About the speaker
Prof. Luo Zhi-Quan received his PhD in Operations Research from the Massachusetts Institute of Technology in 1989. He then joined the McMaster University as an Assistant Professor of Electrical and Computer Engineering and later moved to the University of Minnesota as a Professor of Electrical and Computer Engineering. In 2014, he was appointed the Vice-President (Academic) and Professor of the Chinese University of Hong Kong, Shenzhen.
Prof. Luo’s research mainly addresses mathematical issues in information sciences, with particular focus on the design, analysis and applications of optimization algorithms. Prof. Luo consults regularly with industry on topics related to signal processing and digital communication.
Prof. Luo received numerous awards including the Paul Y. Tseng Memorial Lectureship in Continuous Optimization by the Mathematical Optimization Society (2018) and the Farkas Prize by the INFORMS Optimization Society (2010). Prof. Luo was elected a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) and a Fellow of the Society for Industrial and Applied Mathematics (SIAM). In 2014, he was also elected a Fellow of the Royal Society of Canada.
