Some Theoretical Properties of GANs
Biau, G., Cadre, B., Sangnier, M., Tanielian, U.
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.
Mar-21-2018
- Country:
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- France
- Île-de-France > Paris
- Paris (0.04)
- Brittany > Ille-et-Vilaine
- Rennes (0.04)
- Île-de-France > Paris
- United Kingdom > England
- Europe
- Genre:
- Research Report > New Finding (0.34)