Gradient penalty from a maximum margin perspective

Alexia Jolicoeur-Martineau, Ioannis Mitliagkas

Keywords: GAN, large margin, SVM

Abstract: A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated. We present a unifying framework of expected margin maximization and show that a wide range of gradient-penalized GANs (e.g., Wasserstein, Standard, Least-Squares, and Hinge GANs) can be derived from this framework. Our results imply that employing gradient penalties induces a large-margin classifier (thus, a large-margin discriminator in GANs). We describe how expected margin maximization helps reduce vanishing gradients at fake (generated) samples, a known problem in GANs. From this framework, we derive a new $L^\infty$ gradient norm penalty with Hinge loss which generally produces equally good (or better) generated output in GANs than $L^2$-norm penalties (based on the Fréchet Inception Distance).

One-sentence Summary: Gradient penalty arises from trying to maximize an expected margin.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=og0NfihEq9