Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation

Abstract

Recent work in variational inference (VI) uses ideas from Monte Carlo estimation to tighten the lower bounds on the log-likelihood that are used as objectives. However, there is no systematic understanding of how optimizing different objectives relates to approximating the posterior distribution. Developing such a connection is important if the ideas are to be applied to inference-i.e., applications that require an approximate posterior and not just an approximation of the log-likelihood. Given a VI objective defined by a Monte Carlo estimator of the likelihood, we use a "divide and couple" procedure to identify augmented proposal and target distributions. The divergence between these is equal to the gap between the VI objective and the log-likelihood. Thus, after maximizing the VI objective, the augmented variational distribution may be used to approximate the posterior distribution.

arXiv commentNeural Information Processing Systems (NeurIPS) 2019

Cited by in corpus (5)

• Markovian Score Climbing: Variational Inference with KL(p||q)
• MCMC Variational Inference via Uncorrected Hamiltonian Annealing
• Variational Marginal Particle Filters
• Automatic Differentiation Variational Inference with Mixtures
• Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization