Realizing GANs via a Tunable Loss Function
share
We introduce a tunable GAN, called α-GAN, parameterized by α∈ (0,∞], which interpolates between various f-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct α-GAN using a supervised loss function, namely, α-loss, which is a tunable loss function capturing several canonical losses. We show that α-GAN is intimately related to the Arimoto divergence, which was first proposed by Österriecher (1996), and later studied by Liese and Vajda (2006). We posit that the holistic understanding that α-GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapse.
READ FULL TEXT