Realizing GANs via a Tunable Loss Function

06/09/2021
by   Gowtham R. Kurri, et al.
0

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

Please sign up or login with your details

Forgot password? Click here to reset