Zhu Han received the B.S. degree in electronic engineering from Tsinghua University, in 1997, and the M.S. and Ph.D. degrees in electrical and computer engineering from the University of Maryland, College Park, in 1999 and 2003, respectively. From 2000 to 2002, he was an R&D Engineer of JDSU, Germantown, Maryland. From 2003 to 2006, he was a Research Associate at the University of Maryland. From 2006 to 2008, he was an assistant professor at Boise State University, Idaho. Currently, he is a John and Rebecca Moores Professor in the Electrical and Computer Engineering Department as well as the Computer Science Department at the University of Houston, Texas. Dr. Han is an NSF CAREER award recipient of 2010, and the winner of the 2021 IEEE Kiyo Tomiyasu Award. He has been an IEEE fellow since 2014, an AAAS fellow since 2020, an IEEE Distinguished Lecturer from 2015 to 2018, and an ACM Distinguished Speaker from 2022-2025. Dr. Han is also a 1% highly cited researcher since 2017.

Speech Title：Mean FieldGames Guided Machine Learning in Distributed Systems

Abstract

Mean field games(MFGs) deal with the study and analysis of differential games (DGs) with a large number of indistinguishable, rational, and heterogeneous players. These methodologies approximate the Nash equilibriums for DGs with symmetric interactions among players. In contrast with classical game theory, where players need to react to every other player separately, MFGs simplify the game by modeling the interaction of a representative player with the collective behavior of the other players. In this talk, we first discuss the basic concepts behind MFGs as well as their difference with classical game theory techniques. Then, we will introduce how MFG can be connected with Artificial Intelligence (AI). Specifically, we will connect MFGs with several popular AI techniques, such as evolutionary neural architecture search with MFG selection mechanism, joint server-selection and handover design for satellite-based federated learning using mean-field evolutionary approach, MFG guided deep reinforcement learning for task placement in cooperative multi-access edge computing. Finally, we conclude with the contributions and advantages that MFG can bring to AI.