Speaker: Li Xiuxian, professor, doctoral advisor, Tongji University

Date: May 10, 2023

Time: 9:50-11:50

Location: Zhixin Building, Block B, 1044

Sponsor: School of Mathematics, Shandong University

Abstract:

Online learning is a popular paradigm for decision making in dynamic even adversarial environments. With the advent of big data and advanced technologies, etc., distributed online optimization and game over multi-agent networks have thus far been increasingly focused in the last decade, where a network of agents commit their decisions via local communication in dynamic environments. They are characterized by cooperative and noncooperative phenomena among all the agents, respectively. This talk aims to introduce distributed online optimization (DOO) and online game (OG) with some cutting-edge developments in several aspects, including the case with coupled inequality constraints and distributed online aggregative optimization, and DOO with control systems with application to autonomous docking for unmanned systems. For each scenario, distributed online algorithms are proposed with guaranteed performances, i.e., sublinear static/dynamic regret and constraint violation or fit.

For more information, please visit:

https://www.view.sdu.edu.cn/info/1020/179120.htm