pith. sign in

McGan: Mean and Covariance Feature Matching GAN

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

stat.ML 1

years

2018 1

verdicts

ACCEPT 1

representative citing papers

Demystifying MMD GANs

stat.ML · 2018-01-04 · accept · novelty 6.0

MMD GANs have unbiased critic gradients but biased generator gradients from sample-based learning, and the Kernel Inception Distance provides a practical new measure for GAN convergence and dynamic learning rate adaptation.

citing papers explorer

Showing 1 of 1 citing paper.

  • Demystifying MMD GANs stat.ML · 2018-01-04 · accept · none · ref 37 · internal anchor

    MMD GANs have unbiased critic gradients but biased generator gradients from sample-based learning, and the Kernel Inception Distance provides a practical new measure for GAN convergence and dynamic learning rate adaptation.