Wasserstein Proximal of GANs
Lin, Alex Tong, Li, Wuchen, Osher, Stanley, Montufar, Guido
–arXiv.org Artificial Intelligence
We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. The approach is based on Wasserstein information geometry. It defines a parametrization invariant natural gradient by pulling back optimal transport structures from probability space to parameter space. We obtain easy-to-implement iterative regularizers for the parameter updates of implicit deep generative models. Our experiments demonstrate that this method improves the speed and stability of training in terms of wall-clock time and Fr\'echet Inception Distance.
arXiv.org Artificial Intelligence
Feb-13-2021
- Country:
- North America
- United States
- South Carolina > Richland County
- Columbia (0.14)
- New Jersey > Mercer County
- Princeton (0.04)
- California > Los Angeles County
- Los Angeles (0.28)
- Long Beach (0.04)
- South Carolina > Richland County
- Canada > Ontario
- Toronto (0.14)
- United States
- Europe
- Switzerland > Basel-City
- Basel (0.04)
- Germany > Saxony
- Leipzig (0.04)
- Switzerland > Basel-City
- Asia
- Middle East > Jordan (0.04)
- Japan > Honshū
- Kansai > Osaka Prefecture > Osaka (0.04)
- North America
- Genre:
- Research Report (0.82)
- Technology: