English

Some Theoretical Properties of GANs

Machine Learning 2018-03-22 v1 Machine Learning

Abstract

Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation. The fundamental principle of GANs is to approximate the unknown distribution of a given data set by optimizing an objective function through an adversarial game between a family of generators and a family of discriminators. In this paper, we offer a better theoretical understanding of GANs by analyzing some of their mathematical and statistical properties. We study the deep connection between the adversarial principle underlying GANs and the Jensen-Shannon divergence, together with some optimality characteristics of the problem. An analysis of the role of the discriminator family via approximation arguments is also provided. In addition, taking a statistical point of view, we study the large sample properties of the estimated distribution and prove in particular a central limit theorem. Some of our results are illustrated with simulated examples.

Keywords

Cite

@article{arxiv.1803.07819,
  title  = {Some Theoretical Properties of GANs},
  author = {G. Biau and B. Cadre and M. Sangnier and U. Tanielian},
  journal= {arXiv preprint arXiv:1803.07819},
  year   = {2018}
}
R2 v1 2026-06-23T00:59:59.919Z