加入支持让我们有继续维护的动力！会员畅享查看所有预告
立即购买
6月10日 | Jan Hannig：Fiducial Generative Models
- 来源：
- 学校官网
- 收录时间：
- 2026-07-09 03:15:59
- 时间：
- 2026-06-10 15:30:00
- 地点：
- 普陀校区理科大楼A1314室
- 报告人：
- Jan Hannig
- 学校：
- 华南师范大学
- 关键词：
- generalized fiducial inference, generative models, uncertainty quantification, truncation-based approach, statistical theory
- 简介：
- While generalized fiducial inference (GFI) and its variants have yielded many theoretical and practical results to parametric inference and uncertainty quantification, applying it to generative models remains challenging. We identify three key issues misspecification, metric choices, and over-parameterization hinder the direct application of the GFI to generative models. In this paper, we propose a novel method based on the framework of generalized fiducial inference, designed to construct distributional estimates over the parameter space given observed data, while also enabling uncertainty quantification for generative models. We employ a truncation-based approach and further provide a theoretical analysis of its behavior under varying truncation parameters. Both theoretical results and empirical evidence suggest that, with an appropriately chosen truncation parameter, the truncated distribution derived from generalized fiducial inference achieves valid coverage of the true parameter and leads to improved generalization performance. Joint Work with Zijie Tian, T. C. M. Lee (UC Davis)
- -/- 3
报告介绍：
While generalized fiducial inference (GFI) and its variants have yielded many theoretical and practical results to parametric inference and uncertainty quantification, applying it to generative models remains challenging. We identify three key issues misspecification, metric choices, and over-parameterization hinder the direct application of the GFI to generative models. In this paper, we propose a novel method based on the framework of generalized fiducial inference, designed to construct distributional estimates over the parameter space given observed data, while also enabling uncertainty quantification for generative models. We employ a truncation-based approach and further provide a theoretical analysis of its behavior under varying truncation parameters. Both theoretical results and empirical evidence suggest that, with an appropriately chosen truncation parameter, the truncated distribution derived from generalized fiducial inference achieves valid coverage of the true parameter and leads to improved generalization performance. Joint Work with Zijie Tian, T. C. M. Lee (UC Davis)
报告人介绍：
Jan Hannig is Kenan Distinguished Professor and Chair of the Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill. His research interests include theoretical statistics, generalized fiducial inference, and applications to biology, engineering, and forensic science. He earned his Mgr (equivalent to M.S.) in mathematics from Charles University in Prague in 1996, and his Ph.D. in statistics and probability from Michigan State University in 2000 under the direction of Professor A.V. Skorokhod. From 2000 to 2008, Dr. Hannig was a faculty member in the Department of Statistics at Colorado State University, where he was promoted to Associate Professor. He joined the University of North Carolina at Chapel Hill in 2008, was promoted to Professor in 2013, and became Kenan Distinguished Professor in 2025. Since 2024, he is serving as Chair of the Department. Dr. Hannig was a Faculty Appointee at the National Institute of Standards and Technology from 2018 to 2024. He is a Fellow of the American Statistical Association and the Institute of Mathematical Statistics, as well as an elected member of the International Statistical Institute. He has served as Principal Investigator or Co-Principal Investigator on several federally funded projects. To date, he has advised or co-advised 31 Ph.D. students and published 99 peer-reviewed publications. He has also served as Associate Editor for multiple journals, including the Journal of the American Statistical Association, Journal of Computational and Graphical Statistics, Sankhya, Statistical Theory and Related Fields, Electronic Journal of Statistics, and Stat.
报告图片：
