Skip to yearly menu bar Skip to main content


Poster

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy

Yingyu Lin · Yian Ma · Yu-Xiang Wang · Rachel Redberg · Zhiqi Bu

Halle B #163

Abstract: Posterior sampling, i.e., exponential mechanism to sample from the posterior distribution, provides ε-pure differential privacy (DP) guarantees and does not suffer from potentially unbounded privacy breach introduced by (ε,δ)-approximate DP. In practice, however, one needs to apply approximate sampling methods such as Markov chain Monte Carlo (MCMC), thus re-introducing the unappealing δ-approximation error into the privacy guarantees. To bridge this gap, we propose the Approximate SAample Perturbation (abbr. ASAP) algorithm which perturbs an MCMC sample with noise proportional to its Wasserstein-infinity (W) distance from a reference distribution that satisfies pure DP or pure Gaussian DP (i.e., δ=0). We then leverage a Metropolis-Hastings algorithm to generate the sample and prove that the algorithm converges in W distance. We show that by combining our new techniques with a localization step, we obtain the first nearly linear-time algorithm that achieves the optimal rates in the DP-ERM problem with strongly convex and smooth losses.

Chat is not available.