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 $T= \tilde{\mathcal{O}}(d/\varepsilon_{\textsf{acc}})$ iterations, we can sample from $p_T$ such that $\text{dist}(p_T, p^*) \leq \varepsilon_{\textsf{acc}} + \tilde{\mathcal{O}}(\epsilon)$, where $\epsilon$ is the fraction of corruptions. We corroborate our theoretical analysis with experiments on both synthetic and real-world data sets for mean estimation, regression and binary classification.

[1]  G. Box NON-NORMALITY AND TESTS ON VARIANCES , 1953 .

[2]  Bruno De Finetti,et al.  The Bayesian Approach to the Rejection of Outliers , 1961 .

[3]  P. J. Huber Robust Regression: Asymptotics, Conjectures and Monte Carlo , 1973 .

[4]  D. Ermak A computer simulation of charged particles in solution. I. Technique and equilibrium properties , 1975 .

[5]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[6]  Miklós Simonovits,et al.  Random Walks in a Convex Body and an Improved Volume Algorithm , 1993, Random Struct. Algorithms.

[7]  James O. Berger,et al.  An overview of robust Bayesian analysis , 1994 .

[8]  R. Tweedie,et al.  Rates of convergence of the Hastings and Metropolis algorithms , 1996 .

[9]  R. Tweedie,et al.  Exponential convergence of Langevin distributions and their discrete approximations , 1996 .

[10]  J. Rosenthal,et al.  Optimal scaling of discrete approximations to Langevin diffusions , 1998 .

[11]  C. Villani,et al.  Generalization of an Inequality by Talagrand and Links with the Logarithmic Sobolev Inequality , 2000 .

[12]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[13]  Radford M. Neal MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.

[14]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[15]  T. L. McCluskey,et al.  An assessment of features related to phishing websites using an automated technique , 2012, 2012 International Conference for Internet Technology and Secured Transactions.

[16]  R. Schilling,et al.  Brownian Motion: An Introduction to Stochastic Processes , 2012 .

[17]  Maxim Sviridenko,et al.  Concentration and moment inequalities for polynomials of independent random variables , 2012, SODA.

[18]  A. Dalalyan Theoretical guarantees for approximate sampling from smooth and log‐concave densities , 2014, 1412.7392.

[19]  Prateek Jain,et al.  Robust Regression via Hard Thresholding , 2015, NIPS.

[20]  É. Moulines,et al.  Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm , 2015, 1507.05021.

[21]  Santosh S. Vempala,et al.  Agnostic Estimation of Mean and Covariance , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[22]  Prateek Jain,et al.  Consistent Robust Regression , 2017, NIPS.

[23]  David M. Blei,et al.  Robust Probabilistic Modeling with Bayesian Data Reweighting , 2016, ICML.

[24]  David B. Dunson,et al.  Robust and Scalable Bayes via a Median of Subset Posterior Measures , 2014, J. Mach. Learn. Res..

[25]  Chong Wang,et al.  A General Method for Robust Bayesian Modeling , 2015, Bayesian Analysis.

[26]  Peter L. Bartlett,et al.  Convergence of Langevin MCMC in KL-divergence , 2017, ALT.

[27]  Pravesh Kothari,et al.  Efficient Algorithms for Outlier-Robust Regression , 2018, COLT.

[28]  Sivaraman Balakrishnan,et al.  Robust estimation via robust gradient estimation , 2018, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[29]  Martin J. Wainwright,et al.  Log-concave sampling: Metropolis-Hastings algorithms are fast! , 2018, COLT.

[30]  Michael I. Jordan,et al.  Sampling can be faster than optimization , 2018, Proceedings of the National Academy of Sciences.

[31]  David B. Dunson,et al.  Robust Bayesian Inference via Coarsening , 2015, Journal of the American Statistical Association.

[32]  Pradeep Ravikumar,et al.  Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression , 2019, COLT.

[33]  Daniel M. Kane,et al.  Robust Estimators in High Dimensions without the Computational Intractability , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[34]  Jerry Li,et al.  Sever: A Robust Meta-Algorithm for Stochastic Optimization , 2018, ICML.