时 间：2024年6月6日10:30 - 11:30
地 点：普陀校区理科大楼A1514
报告人：韩锦晖 多伦多大学 博士后
主持人：颜廷进 华东师范大学 助理教授
摘 要：
In the first part, we consider a data-driven newsvendor problem, where one has access to past demand data and the associated feature information. We solve the problem by estimating the target quantile function using a deep neural network (DNN). We provide theoretical guarantees in terms of excess risk bounds for the DNN solution characterized by the network structure and sample size in a non-asymptotic manner, which justify the applicability of DNNs in the relevant contexts. Specifically, the convergence rate of the excess risk bound with respect to the sample size increases in the smoothness of the target quantile function but decreases in the dimension of feature variables. This rate can be further accelerated when the target function possesses a composite structure. Finally, we apply the DNN method to a real-world dataset and confirm its good performance when the sample size is either very large or relatively limited. The newsvendor decision-making is further analyzed in the contexts of operational risk management and spatial allocation planning.
报告人简介：
Jinhui Han is currently a postdoctoral fellow at Rotman School of Management, University of Toronto, and he will join the Guanghua School of Management at Peking University as an assistant professor. His primary research interests lie in using data-driven and stochastic models to address operations management challenges, such as inventory and revenue management problems. He also has a strong interest in interdisciplinary aspects of operations management, encompassing statistical learning, financial engineering, and applied probability.
