Connections between SVMs, Wasserstein distance and GANs

Check out my new paper entitled "Support Vector Machines, Wasserstein's distance and gradient-penalty GANs are connected"! In this paper, we explain how one can derive SVMs and gradient penalized GANs (or those with Lipschitz-1 discriminator) from the same framework! We also show new gradient penalties that lead to better GANs. This paper may completely change your perspective on the Wasserstein's distance, Wasserstein GAN (WGAN), Hinge GAN (HingeGAN), and the use of gradient penalties in GANs. At least, it did for me!