讲座信息
题目:Causal partial identification via optimal transport
报告人:Zijun Gao (USC Marshall Business School)
时间:2026.09.02 19:30
联系人:罗姗姗(北京工商大学)
报告摘要
In causal inference, only one of multiple potential outcomes is observed for each unit, leaving many causal quantities only partially identified (PI). This missingness closely parallels the optimal transport (OT) problem, where marginal distributions are observed but the joint coupling between them is unknown. In this talk, we formalize this connection by casting the causal partial identification problem within the OT framework, enabling the PI sets to be analyzed using tools from the rapidly developing optimal transport literature. When treatment effects are heterogeneous, incorporating covariate information can further sharpen the PI sets. We then generalize the OT formulation to a conditional optimal transport (COT) framework and develop new statistical tools for COT to extend the analysis of PI sets. We conclude by discussing real-world applications and future research directions.
报告人简介
Zijun Gao is a tenure-track assistant professor in the Department of Data Sciences and Operations at USC Marshall Business School. She received her Ph.D. in Statistics from Stanford University in 2022 supervised by Professor Trevor Hastie. She served as a research associate in the Statistical Lab at the University of Cambridge from 2022 to 2023 hosted by Professor Qingyuan Zhao. Her research focuses on the estimation and inference problems in causal inference with heterogeneity, with side interests in distribution learning, selective inference, and model evaluation. She also works on real-world data motivated topics, with a specific emphasis on the applications in adaptive clinical trial and personalized medication.