Generative Adversarial Networks as Variational Training of Energy Based Models

arXiv: Learning, Volume abs/1611.01799, 2017.

Cited by: 6|Views30
EI
Weibo:
We have proposed variational GANs, a family of methodologies to train deep energy based model with an auxiliary variational distribution

Abstract:

In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density $p(mathbf{x})$ is approximated by a variational distribution $q(mathbf{x})$ that is easy to sa...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments