Skip to content (access key 's')
Logo of Technion
Logo of CS Department


Data Science & Deep Learning: An Online Learning Approach to Generative Adversarial Networks
event speaker icon
Kfir Levy (EE, Technion)
event date icon
Monday, 6.1.2020, 12:30
event location icon
Taub 301 Taub Bld.
We consider the problem of training and evaluating generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this work, we view the problem of training GANs as finding a mixed strategy in a zero-sum game. This leads to a new training method that builds upon ideas from game theory and online learning. We provide theoretical guarantees, and develop an efficient heuristic guided by our theoretical results, which we apply to commonly used GAN architectures. On several tasks our approach exhibits improved stability and performance compared to standard GAN training.
[Back to the index of events]