Convergence of GANs Training: A Game and Stochastic Control Methodology

Training of generative adversarial networks (GANs) is known for its difficulty to converge. This paper first confirms analytically one of the culprits behind this convergence issue: the lack of convexity in GANs objective functions, hence the well-posedness problem of GANs models. Then, it proposes a stochastic control approach for hyper-parameters tuning in GANs training. In particular, it presents an optimal solution for adaptive learning rate which depends on the convexity of the objective function, and builds a precise relation between improper choices of learning rate and explosion in GANs training. Finally, empirical studies demonstrate that training algorithms incorporating this selection methodology outperform standard ones.