Bayesian Inference with Posterior Regularization and applications to Infinite Latent SVMs

TL;DR

This paper introduces RegBayes, a flexible Bayesian inference framework with posterior regularization, and demonstrates its effectiveness through applications to infinite latent SVMs for classification and multi-task learning.

Contribution

It proposes a novel regularized Bayesian inference framework and applies it to develop infinite latent SVM models, combining large-margin learning with Bayesian nonparametrics.

Findings

Empirical results show improved classification accuracy on benchmark datasets.

RegBayes offers a more flexible alternative to prior-based Bayesian models.

The approach effectively combines large-margin principles with nonparametric Bayesian methods.

Abstract

Existing Bayesian models, especially nonparametric Bayesian methods, rely on specially conceived priors to incorporate domain knowledge for discovering improved latent representations. While priors can affect posterior distributions through Bayes' rule, imposing posterior regularization is arguably more direct and in some cases more natural and general. In this paper, we present regularized Bayesian inference (RegBayes), a novel computational framework that performs posterior inference with a regularization term on the desired post-data posterior distribution under an information theoretical formulation. RegBayes is more flexible than the procedure that elicits expert knowledge via priors, and it covers both directed Bayesian networks and undirected Markov networks whose Bayesian formulation results in hybrid chain graph models. When the regularization is induced from a linear operator on the posterior distributions, such as the expectation operator, we present a general convex-analysis theorem to characterize the solution of RegBayes. Furthermore, we present two concrete examples of RegBayes, infinite latent support vector machines (iLSVM) and multi-task infinite latent support vector machines (MT-iLSVM), which explore the large-margin idea in combination with a nonparametric Bayesian model for discovering predictive latent features for classification and multi-task learning, respectively. We present efficient inference methods and report empirical studies on several benchmark datasets, which appear to demonstrate the merits inherited from both large-margin learning and Bayesian nonparametrics. Such results were not available until now, and contribute to push forward the interface between these two important subfields, which have been largely treated as isolated in the community.