Event details Event cancelled
Lecture by Professor Jong-Shi Pang, Epstein Family Professor of Industrial and Systems Engineering at the University of Southern California.
The presentation focuses on a unified framework for the design and analysis of distributed algorithm for computing of first-order stationary solutions for non-cooperative games with non-differentiable player objective functions.
These games are closely associated with multi-agent optimization, wherein a large number of selfish players compete non-cooperatively to optimize their individual objectives under various constraints. Unlike centralized algorithms that require a certain system mechanism to coordinate the players’ actions, distributed algorithms have the advantage that the players, either individually or in subgroups, can each make their best responses without full information of their rivals’ actions.
These distributed algorithms are by nature particularly suited to solve games where the large number of players in the game makes the coordination of the players almost impossible. There are two general approaches to establish the convergence of these algorithms - contraction versus potential based, each requiring different properties of the players’ objective functions.
The presentation discusses the details of the convergence analysis based on these two approaches as well as the randomized extensions of the algorithms that require less coordination and hence are more suitable for big data problems.
Professor Jong-Shi Pang, Epstein Family Professor of Industrial and Systems Engineering at the University of Southern California.