Title: Minimax optimal goodness-of-fit testing under local differential privacy
Authors: Joseph Lam-Weil - Magdeburg University (Germany) [presenting]
Jean-Michel Loubes - University of Toulouse (France)
Beatrice Laurent-Bonneau - INSA Toulouse (France)
Abstract: The consequences of local differential privacy constraints on goodness-of-fit testing are considered, i.e. the statistical problem assessing whether sample points are generated from a fixed density or not. The observations are hidden and replaced by a stochastic transformation satisfying the local differential privacy constraint. The focus will be on the lower bound, leading to the minimax optimality of our result over Besov balls.