Fisher GAN

Abstract

Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs. Fisher GAN defines a… (More)

Topics

6 Figures and Tables

Cite this paper

@inproceedings{Mroueh2017FisherG, title={Fisher GAN}, author={Youssef Mroueh and Tom Sercu}, booktitle={NIPS}, year={2017} }