Avoiding Latent Variable Collapse With Generative Skip Models

Adji Bousso Dieng
Adji Bousso Dieng

international conference on artificial intelligence and statistics, 2018.

Cited by: 61|Bibtex|Views150
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Variational autoencoders (VAEs) learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as variable collapse, especially if the lik...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments