differential privacy

Wednesday, June 19, 2019 - 9:00am - 9:50am
Audra McMillan (University of California, Berkeley)
Hypothesis testing plays a central role in statistical inference, and is used in many settings where privacy concerns are paramount. In this talk we’ll address 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-differential privacy, and what sort of tests have optimal sample complexity?
Subscribe to RSS - differential privacy