A Study on Distribution Learning of Generative Adversarial Networks

Abstract

This thesis is an exploration of the properties of shallow generative adversarial networks (GANs). We focus on several aspects of GANs to investigate the learnability of a class of distributions using shallow GANs and conduct experiments to explore the influence of these aspects on the performance of the GAN models. We identify and analyze several pathological phenomena in theoretical analysis and experiments, and propose potential solutions for them.