3 years ago

A Variational Inequality Perspective on Generative Adversarial Networks.

Pascal Vincent, Simon Lacoste-Julien, Hugo Berard, Gauthier Gidel

Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN objective. Yet, surprisingly few studies have looked at optimization methods designed for this adversarial training. In this work, we survey the "variational inequality" framework which contains most formulations of GANs introduced so far. Tapping into the mathematical programming literature, we counter some common misconceptions about the difficulties of saddle point optimization and propose to extend standard methods designed for variational inequalities to the training of GANs. Amongst others, we apply a stochastic version of the extragradient method (SEM) to this task, and propose a novel cheaper variant (OneSEM).

Publisher URL: http://arxiv.org/abs/1802.10551

DOI: arXiv:1802.10551v2

You might also like
Never Miss Important Research

Researcher is an app designed by academics, for academics. Create a personalised feed in two minutes.
Choose from over 15,000 academics journals covering ten research areas then let Researcher deliver you papers tailored to your interests each day.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.