B1510
Title: Estimating functionals under local differential privacy
Authors: Lukas Steinberger - University of Vienna (Austria) [presenting]
Abstract: In this talk we discuss recent advances on a general theory for minimax optimally estimating linear and nonlinear functionals of the data generating distribution when the original data are protected by a local differential privacy constraint. We highlight how the theory of local differential privacy deviates fundamentally from the classical one and exhibit a few entirely new and perhaps surprising phenomena.