We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popular benchmark problems for image generation.
@article{arxiv.1803.05573,
title = {Improving GANs Using Optimal Transport},
author = {Tim Salimans and Han Zhang and Alec Radford and Dimitris Metaxas},
journal= {arXiv preprint arXiv:1803.05573},
year = {2018}
}