English

McGan: Mean and Covariance Feature Matching GAN

Machine Learning 2017-06-12 v2 Machine Learning

Abstract

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and covariance feature matching IPMs allow for stable training of GANs, which we will call McGan. McGan minimizes a meaningful loss between distributions.

Keywords

Cite

@article{arxiv.1702.08398,
  title  = {McGan: Mean and Covariance Feature Matching GAN},
  author = {Youssef Mroueh and Tom Sercu and Vaibhava Goel},
  journal= {arXiv preprint arXiv:1702.08398},
  year   = {2017}
}

Comments

15 pages; published at ICML 2017