Hands-On Generative Adversarial Networks with Keras

Do GANs do distribution learning?

In their paper, Generalization and Equilibrium in Generative Adversarial Nets (GANs), Sanjeev Arora et al. use the birthday paradox to suggest that GANs learn distribution fairly low levels of support. At the same time, in their paper, A Style-Based Generator Architecture for Generative Adversarial Networks, Tero Karras et al. proposed that a GAN architecture is capable of generating many high-quality faces, thus suggesting that GANs have to learn a distribution with rather high levels of support. We should bear this in mind and evaluate our GANs according to the tasks that we build them for.