Search

MiS Preprint Repository

Delve into the future of research at MiS with our preprint repository. Our scientists are making groundbreaking discoveries and sharing their latest findings before they are published. Explore repository to stay up-to-date on the newest developments and breakthroughs.

MiS Preprint
13/2019

Wasserstein of Wasserstein Loss for Learning Generative Models

Yonatan Dukler, Wuchen Li, Alex Tong Lin and Guido Montúfar

Abstract

The Wasserstein distance serves as a loss function for unsupervised learning which depends on the choice of a ground metric on sample space. We propose to use a Wasserstein distance as the ground metric on the sample space of images. This ground metric is known as an effective distance for image retrieval, since it correlates with human perception. We derive the Wasserstein ground metric on image space and define a Riemannian Wasserstein gradient penalty to be used in the Wasserstein Generative Adversarial Network (WGAN) framework. The new gradient penalty is computed efficiently via convolutions on the L2 (Euclidean) gradients with negligible additional computational cost. The new formulation is more robust to the natural variability of images and provides for a more continuous discriminator in sample space.

Received:
Jan 29, 2019
Published:
Jan 30, 2019
Keywords:
Wasserstein metric, GAN, statistical manifold

Related publications

inBook
2019 Journal Open Access
Yonatan Dukler, Wuchen Li, Alex Tong Lin and Guido Montúfar

Wasserstein of Wasserstein loss for learning generative models

In: Proceedings of the 36th international conference on machine learning, 9-15 June 2019, Long Beach, California, USA / Kamalika Chaudhuri (ed.)
Long Beach, California : PMLR, 2019. - pp. 1716-1725
(Proceedings of machine learning research ; 97)
Preprint
2020 Repository Open Access
Yonatan Dukler, Wuchen Li, Alex Tong Lin and Guido Montúfar

Wasserstein of Wasserstein loss for generative models - WWGAN [Computer code]