Adaptive variational Bayes: Optimality, computation and applications

Abstract

In this paper, we explore adaptive inference based on variational Bayes. Although several studies have been conducted to analyze the contraction properties of variational posteriors, there is still a lack of a general and computationally tractable variational Bayes method that performs adaptive inference. To fill this gap, we propose a novel adaptive variational Bayes framework, which can operate on a collection of models. The proposed framework first computes a variational posterior over each individual model separately and then combines them with certain weights to produce a variational posterior over the entire model. It turns out that this combined variational posterior is the closest member to the posterior over the entire model in a predefined family of approximating distributions. We show that the adaptive variational Bayes attains optimal contraction rates adaptively under very general conditions. We also provide a methodology to maintain the tractability and adaptive optimality of the adaptive variational Bayes even in the presence of an enormous number of individual models, such as sparse models. We apply the general results to several examples, including deep learning and sparse factor models, and derive new and adaptive inference results. In addition, we characterize an implicit regularization effect of variational Bayes and show that the adaptive variational posterior can utilize this.

References in corpus (11)

• Convergence rates of posterior distributions for noniid observations
• From $\epsilon$-entropy to KL-entropy: Analysis of minimum information complexity density estimation
• On the properties of variational approximations of Gibbs posteriors
• Bayesian model selection consistency and oracle inequality with intractable marginal likelihood
• On Statistical Optimality of Variational Bayes
• Variational approximations of empirical Bayes posteriors in high-dimensional linear models
• Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee
• Spike and slab Bayesian sparse principal component analysis
• Nonparametric Bayesian model selection and averaging
• Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference
• Bayesian Sparse Gaussian Mixture Model in High Dimensions