Probabilistic Matching of Real and Generated Data Statistics in Generative Adversarial Networks

Generative adversarial networks constitute a powerful approach to generative modeling. While generated samples often are indistinguishable from real data, mode-collapse may occur and there is no guarantee that they will follow the true data distribution. For scientific applications in particular, it is essential that the true distribution is well captured by the generated distribution. In this work, we propose a method to ensure that the distributions of certain generated data statistics coincide with the respective distributions of the real data. …

adversarial applications cs.lg data distribution generated generative generative adversarial networks generative modeling modeling networks real data samples statistics stat.ml true will