Nonparametric Inference for Auto-Encoding Variational Bayes
This work addresses the problem of learning interpretable and scalable latent representations for machine learning practitioners, though it appears incremental as it hybridizes existing methods.
The paper tackles the challenge of combining the interpretable low-dimensional latent representations of Gaussian Process Latent Variable Models with the scalability and flexibility of Variational Autoencoders, resulting in a novel inference scheme that allows for arbitrarily large generative capacity without sacrificing interpretability.
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.