Hamiltonian Variational Auto-Encoder

TL;DR

This paper introduces the Hamiltonian Variational Auto-Encoder (HVAE), a novel approach that leverages Hamiltonian importance sampling to produce low-variance, unbiased estimators of the ELBO and its gradients, enhancing VAE inference.

Contribution

It presents a method to optimally select reverse kernels and build a low-variance estimator using Hamiltonian importance sampling, enabling efficient reparameterization in VAEs.

Findings

Provides a scheme for low-variance unbiased ELBO estimation

Enables reparameterization trick with Hamiltonian importance sampling

Develops a target-informed normalizing flow approach

Abstract

Variational Auto-Encoders (VAEs) have become very popular techniques to perform inference and learning in latent variable models as they allow us to leverage the rich representational power of neural networks to obtain flexible approximations of the posterior of latent variables as well as tight evidence lower bounds (ELBOs). Combined with stochastic variational inference, this provides a methodology scaling to large datasets. However, for this methodology to be practically efficient, it is necessary to obtain low-variance unbiased estimators of the ELBO and its gradients with respect to the parameters of interest. While the use of Markov chain Monte Carlo (MCMC) techniques such as Hamiltonian Monte Carlo (HMC) has been previously suggested to achieve this [23, 26], the proposed methods require specifying reverse kernels which have a large impact on performance. Additionally, the resulting unbiased estimator of the ELBO for most MCMC kernels is typically not amenable to the reparameterization trick. We show here how to optimally select reverse kernels in this setting and, by building upon Hamiltonian Importance Sampling (HIS) [17], we obtain a scheme that provides low-variance unbiased estimators of the ELBO and its gradients using the reparameterization trick. This allows us to develop a Hamiltonian Variational Auto-Encoder (HVAE). This method can be reinterpreted as a target-informed normalizing flow [20] which, within our context, only requires a few evaluations of the gradient of the sampled likelihood and trivial Jacobian calculations at each iteration.