Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

We present a fully Bayesian autoencoder model that treats both local latent variables and global decoder parameters in a Bayesian fashion. This approach allows for flexible priors and posterior approximations while keeping the inference costs low. To achieve this, we introduce an amortized MCMC appr...

Full description

Bibliographic Details

Published in:	Proceedings of machine learning research Vol. 202; p. 34409
Main Authors:	Tran, Ba-Hien, Shahbaba, Babak, Mandt, Stephan, Filippone, Maurizio
Format:	Journal Article
Language:	English
Published:	United States 01.07.2023
ISSN:	2640-3498, 2640-3498
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!