Some Theoretical Properties of GANs

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-01737975
Contributor : Biau Gérard <>
Submitted on : Tuesday, March 20, 2018 - 9:52:46 AM
Last modification on : Wednesday, May 15, 2019 - 3:39:35 AM
Long-term archiving on : Tuesday, September 11, 2018 - 9:27:49 AM

Files

adversarial.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01737975, version 1
  • ARXIV : 1803.07819

Citation

G. Biau, B. Cadre, M. Sangnier, U. Tanielian. Some Theoretical Properties of GANs. 2018. ⟨hal-01737975⟩

Share

Metrics

Record views

190

Files downloads

93