13/04/2021

Scalable gaussian process variational autoencoders

Metod Jazbec, Matt Ashman, Vincent Fortuin, Michael Pearce, Stephan Mandt, Gunnar Rätsch

Keywords:

Abstract Paper Similar Papers

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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AISTATS 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 0
 14:13 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 18:58 
 0
 0
 0
 0
 16:27 
 0
 0
 1
 1
 14:35 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 13:03 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 10:10 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 11:08 
 0
 0
 1
 2
 5:03 
 0
 0
 0
 0
 18:06 
 0
 0
 0
 0
 10:14 
 0
 0
 0
 0
 9:56 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 13:56 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 13:14 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 19:28 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 11:59 
 0
 0
 0
 0
 9:08 
 0
 0
 0
 2
 4:57 
 0
 0
 0
 0
 13:45 
 0
 0
 0
 0
 12:10 
 0
 0
 0
 0
 3:33