Research Talk：

Title：Calibration and Decision Making: An Information Design Perspective

中文题目：校准与决策：信息设计视角

Lecture Topic：

Online Learning and Mechanism Design

中文：在线学习和机制设计

Time and Place：

2026年3月24日上午10：00-12：00 学术讲座和交流，地点：管理科研楼1018

2026年3月25日下午14：00-17：00 课程讲座，地点：管理科研楼801

2026年3月26日上午9：30-12：00和下午14:00-17:00 课程讲座，地点：管理科研楼1018

主讲人: Dr. Feng Yiding, Assistant Professor, Department of Industrial Systems Engineering and Decision Analytics, Hong Kong University of Science and Technology

Bio:

He is an assistant professor of Industrial Engineering and Decision Analytics at the Hong Kong University of Science and Technology (HKUST) since August 2024. He received his Ph.D. degree from the Department of Computer Science, Northwestern University in 2021 and his B.S. degree from ACM Honors Class at Shanghai Jiao Tong University. His current research focuses on developing algorithms and policies in online marketplaces. He has primarily addressed problems utilizing methodologies from online algorithms, approximation algorithms, mechanism design, and information design.

照片：

Abstract:

Modern machine learning models—such as large language models—are increasingly accurate at making predictions, and their outputs are often used by downstream decision-makers to guide actions. For these predictions to be truly useful, however, they must not only be accurate but also reliable. A key criterion for reliability is calibration, which ensures that predicted probabilities align with actual outcomes. In this talk, I present an information-design perspective on calibrated prediction. I will introduce a general framework for comparing the informativeness of different machine predictors, and show how this lens helps us understand the limits and possibilities of calibration. I will then discuss how to optimize predictors in environments where decision-makers’ incentives may be misaligned with those of the predictor. In addition, motivated by practical problems in strategic decision-making, I will also introduce online learning and mechanism design for postgraduate students in this lecture series.