Scalable Gaussian Process Variational Autoencoders

Metod Jazbec · Matt Ashman · Vincent Fortuin · Michael Pearce · Stephan Mandt · Gunnar R├Ątsch


Keywords: [ Probabilistic Methods ] [ Generative and Latent Variable Models ]

[ Abstract ]
[ Slides
Wed 14 Apr 6 a.m. PDT — 8 a.m. PDT


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.

Chat is not available.