Corpus ID: 204575814

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs

@article{JolicoeurMartineau2019ConnectionsBS,
  title={Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs},
  author={Alexia Jolicoeur-Martineau and Ioannis Mitliagkas},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.06922}
}
  • Alexia Jolicoeur-Martineau, Ioannis Mitliagkas
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We generalize the concept of maximum-margin classifiers (MMCs) to arbitrary norms and non-linear functions. Support Vector Machines (SVMs) are a special case of MMC. We find that MMCs can be formulated as Integral Probability Metrics (IPMs) or classifiers with some form of gradient norm penalty. This implies a direct link to a class of Generative adversarial networks (GANs) which penalize a gradient norm. We show that the Discriminator in Wasserstein, Standard, Least-Squares, and Hinge GAN with… CONTINUE READING