papers AI Learner
The Github is limit! Click to go to the new site.

Towards Distributed Coevolutionary GANs

2018-08-31
Abdullah Al-Dujaili, Tom Schmiedlechner, and Erik Hemberg, Una-May O'Reilly

Abstract

Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. Despite their demonstrated success on multiple vision tasks, GANs are difficult to train and much research has been dedicated towards understanding and improving their gradient-based learning dynamics. Here, we investigate the use of coevolution, a class of black-box (gradient-free) co-optimization techniques and a powerful tool in evolutionary computing, as a supplement to gradient-based GAN training techniques. Experiments on a simple model that exhibits several of the GAN gradient-based dynamics (e.g., mode collapse, oscillatory behavior, and vanishing gradients) show that coevolution is a promising framework for escaping degenerate GAN training behaviors.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1807.08194

PDF

https://arxiv.org/pdf/1807.08194


Similar Posts

Comments