Optimal Statistical Estimation under Nonstatistical Constraints
Abstract:
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.
Bio:
Education:
Ph.D., Cornell University, 1996.
Academic Appointments:
Daniel H. Silberberg Professor, Professor of Statistics and Data Science, The Wharton School.
Professor, Applied Math. & Computational Science Graduate Group.
Associate Scholar, Dept. of Biostatistics, Epidemiology, & Bioinformatics, Perelman School of Medicine.
Administrative Appointment:
Vice Dean for China Initiatives, The Wharton School, 2017-2020
Editorial Appointments:
Editor, The Annals of Statistics, 2010-2012
Associate Editor, Journal of the Royal Statistical Society, Series B, 2014-2018
Associate Editor, Journal of the American Statistical Association, 2005-2010
Associate Editor, The Annals of Statistics, 2004-2009
Associate Editor, Statistica Sinica, 2005-2011
Associate Editor, Statistics Surveys, 2006-2009
Editorial Board, Frontiers of Statistics book series, 2009-present
Guest Editor, Statistica Sinica Special Issue on Multiscale Methods
Guest Editor, Journal of Nonparametric Statistics Special Issue for the Inaugural IMS-China International Conference
Honors & Awards:
Laplace Lecturer of the Bernoulli Society, 10th World Congress in Probability & Statistics, 2021
International Chinese Statistical Association Distinguished Achievement Award, 2019
Peter Whittle Lecturer, Cambridge University, 2018
ICCM Best Paper Award, 2018
President, the International Chinese Statistical Association, 2017
Hermann Otto Hirschfeld Lecturer, Humboldt-Universität zu Berlin, 2012
Forum Lecturer, 28th European Meeting of Statisticians, Piraeus, Greece, 2010
Medallion Lecturer, Institute of Mathematical Statistics, 2009