Consistency of ELBO maximization for model selection

Abstract

The Evidence Lower Bound (ELBO) is a quantity that plays a key role in variational inference. It can also be used as a criterion in model selection. However, though extremely popular in practice in the variational Bayes community, there has never been a general theoretic justification for selecting based on the ELBO. In this paper, we show that the ELBO maximization strategy has strong theoretical guarantees, and is robust to model misspecification while most works rely on the assumption that one model is correctly specified. We illustrate our theoretical results by an application to the selection of the number of principal components in probabilistic PCA.

References in corpus (1)

• Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixtures

Cited by in corpus (5)

• MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancy
• Convergence Rates of Variational Inference in Sparse Deep Learning
• A Generalization Bound for Online Variational Inference
• Causal, Bayesian, & Non-parametric Modeling of the SARS-CoV-2 Viral Load Distribution vs. Patient's Age
• Adaptive variational Bayes: Optimality, computation and applications