Seminar by Prof. T. Tony CAI from Department of Statistics and Data Science, The Wharton School, University of Pennsylvania

In the conventional statistical framework, a major goal is to develop optimal statistical procedures based on the sample size and statistical model. However, in many contemporary applications, non-statistical concerns such as privacy and communication constraints associated with the statistical procedures become crucial. This raises a fundamental question in data science: how can we make optimal statistical inference under these non-statistical constraints?

In this talk, we explore recent advances in differentially private learning and distributed learning under communication constraints in a few specific settings. Our results demonstrate novel and interesting phenomena and suggest directions for further investigation.

Tony Cai is the Daniel H. Silberberg Professor at Department of Statistics and Data Science, The Wharton School, University of Pennsylvania. Tony is a worldwide well-known statistician with the COPSS Presidents' Award in 2008. Tony’s research areas include, but not are not limited to, Statistical machine learning, High-dimensional statistics, Large-scale inference and Statistical decision theory, and he has a long list of endless publications. Tony was the co-editor of the Annals of Statistics, and has served as the associate editor for all top statistical journals. Tony was the president of the International Chinese Statistical Association (ICSA).