Bayesian Robustness: A Nonasymptotic Viewpoint

We study the problem of robustly estimating the posterior distribution for the setting where observed data can be contaminated with potentially adversarial outliers. We propose Rob-ULA, a robust variant of the Unadjusted Langevin Algorithm (ULA), and provide a finite-sample analysis of its sampling distribution. In particular, we show that after T = O (d/eacc) iterations, we can sample from pT such that dist(pT, p*) = e(acc) + O(e), where e is the fraction of corruptions and dist represents the squared 2-Wasserstein distance metric. Our results for the class of posteriors p* which satisfy log-concavity and smoothness assumptions. We corroborate our theoretical analysis with experiments on both synthetic and real-world datasets for mean estimation, regression and binary classification. Supplementary materials for this article are available online.