Resampled Priors for Variational Autoencoders

Understand

We propose Learned Accept/Reject Sampling (LARS), a method for constructing richer priors using rejection sampling with a learned acceptance function.

• This work is motivated by recent analyses of the VAE objective, which pointed out that commonly used simple priors can lead to underfitting.
• As the distribution induced by LARS involves an intractable normalizing constant, we show how to estimate it and its gradients efficiently.
• We demonstrate that LARS priors improve VAE performance on several standard datasets both when they are learned jointly with the rest of the model and when they are fitted to a pretrained model.