Structure-preserving GANs. (arXiv:2202.01129v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2202.01129

Generative adversarial networks (GANs), a class of distribution-learning
methods based on a two-player game between a generator and a discriminator, can
generally be formulated as a minmax problem based on the variational
representation of a divergence between the unknown and the generated
distributions. We introduce structure-preserving GANs as a data-efficient
framework for learning distributions with additional structure such as group
symmetry, by developing new variational representations for divergences. Our
theory shows that we can reduce the discriminator space to its …

arxiv gans lg