讲座题目 | Efficient and Interpretable Algorithms for Intelligent Matching | ||
主讲人 （单位） | 张海伦 香港中文大学（深圳） | 主持人 （单位） | 李四杰，王杰 （东南大学） |
讲座时间 | 2025年4月27日16:00 | 讲座地点 | 经管楼B201 |
主讲人简介 |
Dr. Hailun Zhang is an assistant professor in School of Data Science (SDS), The Chinese University of Hong Kong, Shenzhen. Before joining CUHKSZ, he is a Postdoc fellow in Department of Industrial Engineering and Decision Analytics at HKUST, where he obtained a Ph.D. degree in July 2018. His research interests lie in flexibility design, queuing networks, online algorithm design and supply chain management. Before HKUST, he received his bachelor and master's degree in Mathematics department from Peking University. He has published papers in top-tier journals like Operations Research, Management Science, Production and Operations Management, etc. | ||
讲座内容摘要 | Intelligent matching is a critical decision-making problem on many real-world platforms, widely applied in areas such as ride-hailing, food delivery, and game matchmaking. These problems are typically characterized by high randomness, high dimensionality, and dynamic decision-making, making it extremely challenging to obtain optimal solutions. Although machine learning methods like reinforcement learning offer new approaches to address such problems, these algorithms still face limitations such as long training cycles, high data dependency, and poor interpretability. To address these challenges, we propose a series of more interpretable and straightforward algorithms from an operations research perspective. These algorithms are not only easy to implement in practical applications but also come with certain theoretical guarantees. Numerical experiments in specific application scenarios demonstrate the significant advantages of our proposed algorithms compared to baseline methods. | ||
