A Unifying Generator Loss Function for Generative Adversarial Networks

arXiv:2308.07233v2 Announce Type: replace
Abstract: A unifying $\alpha$-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator loss function such as the one in the original GAN (VanillaGAN) system. The generator loss function is based on a symmetric class probability estimation type function, $\mathcal{L}_\alpha$, and the resulting GAN system is termed $\mathcal{L}_\alpha$-GAN. Under an optimal discriminator, it is shown that the generator's optimization problem consists of minimizing a Jensen-$f_\alpha$-divergence, a …

abstract adversarial alpha arxiv canonical class cs.lg function gan generative generative adversarial network generative adversarial networks generator loss network networks probability type