Realizing GANs via a Tunable Loss Function

Abstract

We introduce a tunable GAN, called $\alpha$-GAN, parameterized by $\alpha \in (0,\infty ]$, which interpolates between various $f$-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct $\alpha$-GAN using a supervised loss function, namely, $\alpha$-loss, which is a tunable loss function capturing several canonical losses. We show that $\alpha$-GAN is intimately related to the Arimoto divergence, which was first proposed by Österriecher (1996), and later studied by Liese and Vajda (2006). We also study the convergence properties of $\alpha$-GAN. We posit that the holistic understanding that $\alpha$-GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapse.

Extended version of a paper accepted to ITW 2021. 8 pages, 2 figures