Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 9403-9413, 2019.

Cited by: 34|Bibtex|Views77
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org
Keywords:

Abstract:

Posterior collapse in Variational Autoencoders (VAEs) arises when the variational posterior distribution closely matches the prior for a subset of latent variables. This paper presents a simple and intuitive explanation for posterior collapse through the analysis of linear VAEs and their direct correspondence with Probabilistic PCA (pPCA)...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments