How to Train Your DRAGAN

  title={How to Train Your DRAGAN},
  author={Naveen Kodali and Jacob D. Abernethy and James Hays and Zsolt Kira},
Generative Adversarial Networks have emerged as an effective technique for estimating data distributions. The basic setup consists of two deep networks playing against each other in a zero-sum game setting. However, it is not understood if the networks reach an equilibrium eventually and what dynamics makes this possible. The current GAN training procedure, which involves simultaneous gradient descent, lacks a clear game-theoretic justification in the literature. In this paper, we introduce… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 113 times over the past 90 days. VIEW TWEETS



Citations per Year

Citation Velocity: 27

Averaging 27 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.