McGan: Mean and Covariance Feature Matching GAN
Youssef Mroueh, Tom Sercu, Vaibhava Goel · arXiv (Cornell University) · 2017
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.