(ε, δ)-Differential Privacy of Gibbs Posteriors

Abstract

The exponential mechanism is a general method to construct a randomized estimator that satisfies (ε, 0)-differential privacy. Recently, Wang et al. [12] showed that the Gibbs posterior, which is a data-dependent probability distribution that contains the Bayesian posterior, is essentially equivalent to the exponential mechanism under certain boundedness… (More)

Topics

2 Figures and Tables