Flexible Prior Distributions for Deep Generative Models

Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann

Feb 15, 2018 (modified: Oct 27, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we argue that it might be advantageous to use more flexible code distributions. We demonstrate how these distributions can be induced directly from the data. The benefits include: more powerful generative models, better modeling of latent structure and explicit control of the degree of generalization.
  • Keywords: Deep Generative Models, GANs
0 Replies