Realizing GANs via a Tunable Loss Function

Gowtham R. Kurri, Tyler Sypherd, Lalitha Sankar

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 constr…