The Structure of Optimal Private Tests for Simple Hypotheses
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, Volume abs/1811.11148, 2019.
differential privacy hypothesis testing
Hypothesis testing plays a central role in statistical inference, and is used in many settings where privacy concerns are paramount. This work answers a basic question about privately testing simple hypotheses: given two distributions P and Q, and a privacy level ε, how many i.i.d. samples are needed to distinguish P from Q subject to ε-d...More
PPT (Upload PPT)