讲座题目：Conformal Prediction in Non-Exchangeable Data Contexts
主讲人：王会霞 教授
主持人：唐炎林 教授
开始时间：2024-06-07 10:00
讲座地址：普陀校区理科大楼A1514
主办单位：统计学院
报告人简介：
Judy Huixia Wang earned her B.S. and M.S. in Statistics from Fudan University in 1995 and 1999, respectively, and her Ph.D. in Statistics from University of Illinois in 2006. She was a faculty member in the Department of Statistics at North Carolina State University from 2006 to 2014. She is currently a Professor and Chair in the Department of Statistics at the George Washington University. She received a CAREER award from the US National Science Foundation and the Tweedie New Researcher Award from the Institute of Mathematical Statistics in 2012. In 2018, she was elected as a Fellow of the American Statistical Association and the Institute of Mathematical Statistics. She was named one of the IMS Medallion Lecturers in 2022, the Mitchell Distinguished Lecturer by the University of Glasgow in 2023, and the Bohrer Lecturer at the University of Illinois at Urbana-Champaign in 2024. She served as a Program Director in the Division of Mathematical Sciences (DMS) of the US National Science Foundation from 2018 to 2022, managing the statistics program in DMS as well as a number of interdisciplinary programs that are cross-directorate and cross-agency. Her research interests include quantile regression, semiparametric and nonparametric regression, high dimensional inference, extreme value analysis, spatial analysis, etc.
报告内容：
Conformal prediction is a distribution-free method for uncertainty quantification that ensures finite sample guarantee. However, its validity relies on the assumption of data exchangeability. In this talk, I will introduce several conformal prediction approaches tailored for non-exchangeable data settings, including clustered data with missing responses, nonignorable missing data, and label shift data. To provide an asymptotic conditional coverage guarantee for a given subject, we propose constructing prediction regions by establishing the highest posterior density region of the target. This method is more accurate under complex error distributions, such as asymmetric and multimodal distributions, making it beneficial for personalized and heterogeneous scenarios. I will present some numerical results to illustrate their effectiveness.
