← Search

Martin Heusel

2 accepted papers

2018

Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields

ICLR 2018poster

Generative adversarial networks (GANs) evolved into one of the most successful unsupervised techniques for generating realistic images. Even though it has recently been shown that GAN training converges, GAN models often end up in local Nash equilibria that are associated with mode collapse or other…

2017

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

NeurIPS 2017poster

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient desc…