专栏名称: 中山大学管理学院

中山大学管理学院成立于1985年，已通过AACSB、EQUIS和AMBA三大国际认证。以“融汇中西管理智慧，培养创业创新精神，践行服务社会责任，作育商界管理精英”为使命。打造中国商界黄埔军校，我们愿与您携手并肩！

讲座预告丨管理学院管理学与经济学系列前沿讲座之四一三讲

中山大学管理学院 · 公众号 · · 2020-12-14 21:13

正文

讲座主题

Learning and Earning Under a Non-stationary Growing Environment

主讲嘉宾

郑泽宇教授（美国加州伯克利大学IEOR系）

主持人

夏俐教授

讲座时间

2020年12月16日（周三）10:00—12:00

讲座形式

线上会议（腾讯会议ID：953840606）

嘉宾简介

郑泽宇博士目前是美国加州伯克利大学工业工程与运筹系助理教授。他从斯坦福大学获得运筹学博士学位和经济学硕士学位，从北京大学获得数学学士学位，他的主要研究方向为仿真、非平稳随机建模与决策、金融科技等。

讲座简介

We consider a single-product dynamic pricing problem under a specific non-stationary setting, where the underlying demand process grows over time in expectation and also possibly in the level of random fluctuation. The decision maker sequentially sets price in each time period and learns the unknown demand model, with the goal of maximizing expected cumulative revenue over the entire time horizon. We prove matching upper and lower bounds on regret and provide near-optimal pricing policies, showing how the growth rate of random fluctuation over time affects the best achievable regret order and the near-optimal policy design. In the analysis, we show that whether the seller knows the length of time horizon in advance or not surprisingly render different optimal regret orders. We then extend the demand model such that the optimal price may vary with time and present a novel and near-optimal policy for the extended model. Finally, we consider an analogous non-stationary setting in the canonical multi-armed bandit problem, and points out that knowing or not knowing the length of time horizon render the same optimal regret order, in contrast to the non-stationary dynamic pricing problem.