Variance Regularizing Adversarial Learning

Understand

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.