Yujie Tang, Assistant Professor, College of Engineering, Peking University

Li Zhang, Doctor

Introduction to Zeroth-Order Optimization and Recent Advances

16:00–17:00 July 19 (Friday), N702

In recent years, there has been a rapidly increasing interest in the study of zeroth-order optimization methods, with applications in areas such as machine learning, data-driven optimization, and control. In the first part of this talk, we will provide a brief tutorial on zeroth-order optimization methods based on zeroth-order gradient estimation techniques. We will introduce various types of zeroth-order gradient estimators, discuss their statistical properties, and analyze the convergence of the resulting algorithms. Special attention will be given to comparing the oracle complexities of zeroth-order methods with their first-order counterparts. In the second part of the talk, we will explore recent advances in zeroth-order optimization, with a particular focus on accelerating the convergence of zeroth-order methods and the applications in multi-agent systems.

个人简介：Yujie Tang received the Bachelor's degree in Electronic Engineering from Tsinghua University, China in 2013, and the Ph.D. degree in Electrical Engineering from the California Institute of Technology, USA in 2019. From 2019 to 2022, he worked as a postdoctoral fellow in the School of Engineering and Applied Sciences at Harvard University. Since 2022, he has served as an assistant professor in the Department of Industrial Engineering and Management at Peking University. His research interests include distributed optimization and zeroth-order optimization, reinforcement learning and data-driven control methods, and optimization methods for power and energy systems.