English

Variance Regularizing Adversarial Learning

Machine Learning 2018-08-21 v2 Machine Learning

Abstract

We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. We hypothesize that this approach ensures a non-zero gradient to the generator, even in the limit of a perfect classifier. We test our method against standard benchmark image datasets as well as show the classifier output distribution is smooth and has overlap between the real and fake modes.

Keywords

Cite

@article{arxiv.1707.00309,
  title  = {Variance Regularizing Adversarial Learning},
  author = {Karan Grewal and R Devon Hjelm and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1707.00309},
  year   = {2018}
}

Comments

Method is out of date and some results are incorrect