Scalable Gaussian Process Variational Autoencoders

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

Text

Jazbec et al. "Scalable Gaussian Process Variational Autoencoders." Artificial Intelligence and Statistics, 2021.

Markdown

[Jazbec et al. "Scalable Gaussian Process Variational Autoencoders." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/jazbec2021aistats-scalable/)

BibTeX

@inproceedings{jazbec2021aistats-scalable,
  title     = {{Scalable Gaussian Process Variational Autoencoders}},
  author    = {Jazbec, Metod and Ashman, Matt and Fortuin, Vincent and Pearce, Michael and Mandt, Stephan and Rätsch, Gunnar},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2021},
  pages     = {3511-3519},
  volume    = {130},
  url       = {https://mlanthology.org/aistats/2021/jazbec2021aistats-scalable/}
}