Speaker：T. Tony Cai(University of Pennsylvania)

Time：2025.7.16 8：50-9：35

Venue：Science Hall

Abstract：In this talk, we consider minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. We first establish the minimax misclassification rate, precisely characterizing the effects of privacy constraints, source samples, and target samples on classificationaccuracy. The results reveal interesting phase transition phenomena and highlight the intricate trade-offs between preserving privacy and achieving classification accuracy. We then develop a data-driven adaptive classifier that achieves the optimal rate within a logarithmic factor across a large collection of parameter spaces while satisfying the sameset of differential privacy constraints. Simulation studies and real-world data applications further elucidate the theoretical analysis with numerical results.

Biography：T. Tony Cai is the Daniel H. Silberberg Professor of Statistics and Data Science at the Wharton School, University of Pennsylvania. He also holds joint appointments as a professor in the Applied Mathematics & Computational Science Graduate Group and as a senior scholar in the Department of Biostatistics, Epidemiology, and Informatics at the Perelman School of Medicine. Tony Cai currently serves as President of the Institute of Mathematical Statistics (IMS). He received the prestigious COPSS Presidents’ Award in 2008 and was elected as a Fellow of the American Association for the Advancement of Science (AAAS) in 2024. He previously served as Editor of the Annals of Statistics (2020–2012), President of the International Chinese Statistical Association (ICSA, 2017), and Vice Dean at the Wharton School (2017–2020). His research spans statistical machine learning, high-dimensional statistics, large-scale multiple testing, decision theory, and nonparametric function estimation, with applications in genomics and financial engineering.