Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

Add code
Jul 04, 2017
Qiang Liu, Dilin Wang
Figure 1 for Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
Figure 2 for Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
Figure 3 for Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
Figure 4 for Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by combining GAN-style methods with traditional energy-based learning.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon