Training Variational Auto Encoders with Discrete Latent Representations using Importance Sampling

Abstract

The Variational Auto Encoder (VAE) is a popular generative latent variable model that is often applied for representation learning. Standard VAEs assume continuous valued latent variables and are trained by maximization of the evidence lower bound (ELBO). Conventional methods obtain a differentiable estimate of the ELBO with reparametrized sampling and optimize it with Stochastic Gradient Descend (SGD). However, this is not possible if we want to train VAEs with discrete valued latent variables, since reparametrized sampling is not possible. Till now, there exist no simple solutions to circumvent this problem. In this paper, we propose an easy method to train VAEs with binary or categorically valued latent representations. Therefore, we use a differentiable estimator for the ELBO which is based on importance sampling. In experiments, we verify the approach and train two different VAEs architectures with Bernoulli and Categorically distributed latent representations on two different benchmark datasets.

Tasks

Reproductions