From GAN to WGAN

Abstract

This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to improve GANs' training by adopting a smooth metric for measuring the distance between two probability distributions.

12 pages, 9 figures

Cited by in corpus (2)

• Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks
• Deblending Galaxies with Generative Adversarial Networks