Arbel, M;
Sutherland, DJ;
Bińkowski, M;
Gretton, A;
(2018)
On gradient regularizers for MMD GANs.
In: Bengio, S and Wallach, H and Larochelle, H and Grauman, K and Cesa-Bianchi, N and Garnett, R, (eds.)
Advances in Neural Information Processing Systems 31 (NIPS 2018).
NIPS Proceedings: Montreal, Canada.
Preview |
Text
smmd.pdf - Published Version Download (9MB) | Preview |
Abstract
We propose a principled method for gradient-based regularization of the critic of GAN-like models trained by adversarially optimizing the kernel of a Maximum Mean Discrepancy (MMD). We show that controlling the gradient of the critic is vital to having a sensible loss function, and devise a method to enforce exact, analytical gradient constraints at no additional cost compared to existing approximate techniques based on additive regularizers. The new loss function is provably continuous, and experiments show that it stabilizes and accelerates training, giving image generation models that outperform state-of-the art methods on 160 × 160 CelebA and 64 × 64 unconditional ImageNet.
Archive Staff Only
 |
View Item |
