Early stopping in GAN

https://www.quora.com/How-can-we-apply-early-stopping-for-Generative-Adversarial-Network-GAN-to-prevent-overfitting

Ian Goodfellow, Lead author of the Deep Learning textbook: http://www.deeplearningbook.org

Answered Dec 27, 2016 · Upvoted by Carson Wu, M.S. Computer Vision & Deep Learning, Tongji University (2019)

Overfitting isn’t much of a problem for GANs: https://arxiv.org/pdf/1611.04273...

Because we aren’t able to find the Nash equilibrium very well, they generall underfit.