Scalable Gaussian Process Variational Autoencoders
Machine Learning
2021-02-25 v3 Machine Learning
Abstract
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs has led to significant improvements in this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GP-VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.
Cite
@article{arxiv.2010.13472,
title = {Scalable Gaussian Process Variational Autoencoders},
author = {Metod Jazbec and Matthew Ashman and Vincent Fortuin and Michael Pearce and Stephan Mandt and Gunnar Rätsch},
journal= {arXiv preprint arXiv:2010.13472},
year = {2021}
}
Comments
Published at AISTATS 2021