MLLGSTMay 9, 2017

Frequentist Consistency of Variational Bayes

arXiv:1705.03439v3233 citations
Originality Highly original
AI Analysis

This provides foundational theoretical support for VB methods, addressing a key gap for researchers and practitioners in Bayesian statistics who rely on scalable inference.

The paper tackles the lack of theoretical guarantees for variational Bayes (VB) methods by establishing frequentist consistency and asymptotic normality, proving that the VB posterior converges to a KL minimizer of a normal distribution centered at the truth and that variational parameter expectations are consistent and asymptotically normal.

A key challenge for modern Bayesian statistics is how to perform scalable inference of posterior distributions. To address this challenge, variational Bayes (VB) methods have emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) methods. VB methods tend to be faster while achieving comparable predictive performance. However, there are few theoretical results around VB. In this paper, we establish frequentist consistency and asymptotic normality of VB methods. Specifically, we connect VB methods to point estimates based on variational approximations, called frequentist variational approximations, and we use the connection to prove a variational Bernstein-von Mises theorem. The theorem leverages the theoretical characterizations of frequentist variational approximations to understand asymptotic properties of VB. In summary, we prove that (1) the VB posterior converges to the Kullback-Leibler (KL) minimizer of a normal distribution, centered at the truth and (2) the corresponding variational expectation of the parameter is consistent and asymptotically normal. As applications of the theorem, we derive asymptotic properties of VB posteriors in Bayesian mixture models, Bayesian generalized linear mixed models, and Bayesian stochastic block models. We conduct a simulation study to illustrate these theoretical results.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes