A General Method for Robust Bayesian Modeling

By Chong Wang, David M. Blei. 2015

65 citations recorded by the source corpus.

Robust Bayesian models are appealing alternatives to standard models, providing protection from data that contains outliers or other departures from the model assumptions. Historically, robust models were mostly developed on a case-by-case basis; examples include robust linear regression, robust mixture models, and bursty topic models. In this paper we develop a general approach to robust Bayesian modeling. We show how to turn an existing Bayesian model into a robust model, and then develop a generic strategy for computing with it. We use our method to study robust variants of several models, including linear regression, Poisson regression, logistic regression, and probabilistic topic models. We discuss the connections between our methods and existing approaches, especially empirical Bayes and James-Stein estimation.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Joint probabilistic modeling of single-cell multi-omic data with totalVI (2021, background): “A prior can also be thought of as regularizing the posterior distribution, thus reducing the influence of outliers [60].”
Gen: a general-purpose probabilistic programming system with programmable inference (2019, background): “Inference in robust Bayesian models is an active research area [45].”
Reweighted Data for Robust Probabilistic Models (2016, background): “This transforms the model into where a top-level latent variable α ties together all the β n variables (de Finetti, 1961; Wang and Blei, 2015).”