Nonparametric Inference for Auto-Encoding Variational Bayes
Abstract
We would like to learn latent representations that are low-dimensional and highly interpretable. A model that has these characteristics is the Gaussian Process Latent Variable Model. The benefits and negative of the GP-LVM are complementary to the Variational Autoencoder, the former provides interpretable low-dimensional latent representations while the latter is able to handle large amounts of data and can use non-Gaussian likelihoods. Our inspiration for this paper is to marry these two approaches and reap the benefits of both. In order to do so we will introduce a novel approximate inference scheme inspired by the GP-LVM and the VAE. We show experimentally that the approximation allows the capacity of the generative bottle-neck (Z) of the VAE to be arbitrarily large without losing a highly interpretable representation, allowing reconstruction quality to be unlimited by Z at the same time as a low-dimensional space can be used to perform ancestral sampling from as well as a means to reason about the embedded data.
Cite
@article{arxiv.1712.06536,
title = {Nonparametric Inference for Auto-Encoding Variational Bayes},
author = {Erik Bodin and Iman Malik and Carl Henrik Ek and Neill D. F. Campbell},
journal= {arXiv preprint arXiv:1712.06536},
year = {2017}
}
Comments
Presented at NIPS 2017 Workshop on Advances in Approximate Bayesian Inference