{
  "id": "2006.11432",
  "version": "v1",
  "published": "2020-06-19T22:54:01.000Z",
  "updated": "2020-06-19T22:54:01.000Z",
  "title": "Online Kernel based Generative Adversarial Networks",
  "authors": [
    "Yeojoon Youn",
    "Neil Thistlethwaite",
    "Sang Keun Choe",
    "Jacob Abernethy"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "One of the major breakthroughs in deep learning over the past five years has been the Generative Adversarial Network (GAN), a neural network-based generative model which aims to mimic some underlying distribution given a dataset of samples. In contrast to many supervised problems, where one tries to minimize a simple objective function of the parameters, GAN training is formulated as a min-max problem over a pair of network parameters. While empirically GANs have shown impressive success in several domains, researchers have been puzzled by unusual training behavior, including cycling so-called mode collapse. In this paper, we begin by providing a quantitative method to explore some of the challenges in GAN training, and we show empirically how this relates fundamentally to the parametric nature of the discriminator network. We propose a novel approach that resolves many of these issues by relying on a kernel-based non-parametric discriminator that is highly amenable to online training---we call this the Online Kernel-based Generative Adversarial Networks (OKGAN). We show empirically that OKGANs mitigate a number of training issues, including mode collapse and cycling, and are much more amenable to theoretical guarantees. OKGANs empirically perform dramatically better, with respect to reverse KL-divergence, than other GAN formulations on synthetic data; on classical vision datasets such as MNIST, SVHN, and CelebA, show comparable performance.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-19T22:54:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "mode collapse",
      "okgans empirically perform dramatically better",
      "online kernel-based generative adversarial networks",
      "vision datasets",
      "major breakthroughs"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}