On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee

Neural Information Processing Systems 

Gaussian, to an unknown data distribution, which is only represented by empirical samples. In order to measure the mapping quality, various metrics between the probability distributions have been proposed.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found