Job Talk: Data-Driven Stochastic Optimization in the Presence of Distributional Uncertainty 发布时间:2024-01-12

  • 活动时间:
  • 活动地址:
  • 主讲人:

题 目:Data-Driven Stochastic Optimization in the Presence of Distributional Uncertainty

嘉 宾:林意璠,博士,Georgia Institute of Technology

主持人:林学民,教授,BAT365唯一官网

时 间:2024113日(周六)9:30-11:00

地 点:腾讯会议(如需会议号和密码,请发邮件至 wanxin.chen@sjtu.edu.cn 获取)


内容简介: Stochastic optimization is a mathematical framework that models decision making under uncertainty. It usually assumes that the decision maker has full knowledge about the underlying uncertainty through a known probability distribution and minimizes (or maximizes) a functional of the cost (or reward) function. However, the probability distribution of the randomness in the system is rarely known in practice and is often estimated from historical data. The goal of the decision maker is therefore to select the optimal decision under this distributional uncertainty. This talk aims to address the distributional uncertainty under different contexts of stochastic optimization by proposing new formulations and devising new approaches.


演讲人简介 Yifan Lin is a fifth-year Ph.D. candidate in Operations Research at H. Milton School of Industrial and Systems Engineering, Georgia Institute of Technology. He received Bachelor degree of Economics in Financial Engineering and Bachelor degree of Engineering in Computer Science from Wuhan University in 2017, and he received Master degree of Science in Operations Research from Columbia University in 2018. He is a recipient of the Best Theoretical Paper Award at the 18th INFORMS Workshop on Data Mining and Decision Analytics. His research interests lie in theory, methods, and applications of simulation, stochastic optimization, and reinforcement learning. He currently works on designing efficient algorithms for sequential decision making under uncertainty.

 

欢迎广大师生参加!