Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
arXiv:1708.08819
Abstract
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 otherwise fail to model the target distribution. We introduce Coulomb GANs, which pose the GAN learning problem as a potential field of charged particles, where generated samples are attracted to training set samples but repel each other. The discriminator learns a potential field while the generator decreases the energy by moving its samples along the vector (force) field determined by the gradient of the potential field. Through decreasing the energy, the GAN model learns to generate samples according to the whole target distribution and does not only cover some of its modes. We prove that Coulomb GANs possess only one Nash equilibrium which is optimal in the sense that the model distribution equals the target distribution. We show the efficacy of Coulomb GANs on a variety of image datasets. On LSUN and celebA, Coulomb GANs set a new state of the art and produce a previously unseen variety of different samples.
Published as a conference paper at ICLR (International Conference on Learning Representations) 2018. Implementation available at https://github.com/bioinf-jku/coulomb_gan
References in corpus (7)
- Energy-based Generative Adversarial Network
- The Loss Surfaces of Multilayer Networks
- Self-Normalizing Neural Networks
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- Mode Regularized Generative Adversarial Networks
- Do GANs actually learn the distribution? An empirical study
- On distinguishability criteria for estimating generative models