Some Theoretical Properties of GANs

03/21/2018
by   G. Biau, et al.
0

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.

READ FULL TEXT

page 13

page 18

page 19

page 21

page 22

page 23

research
06/29/2018

Convergence Problems with Generative Adversarial Networks (GANs)

Generative adversarial networks (GANs) are a novel approach to generativ...
research
01/30/2021

Rates of convergence for density estimation with GANs

We undertake a precise study of the non-asymptotic properties of vanilla...
research
05/24/2017

Approximation and Convergence Properties of Generative Adversarial Learning

Generative adversarial networks (GAN) approximate a target data distribu...
research
06/27/2018

Approximability of Discriminators Implies Diversity in GANs

While Generative Adversarial Networks (GANs) have empirically produced i...
research
01/18/2022

Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs

Arguably the most fundamental question in the theory of generative adver...
research
12/06/2020

Contrastive Divergence Learning is a Time Reversal Adversarial Game

Contrastive divergence (CD) learning is a classical method for fitting u...
research
10/30/2017

Implicit Manifold Learning on Generative Adversarial Networks

This paper raises an implicit manifold learning perspective in Generativ...

Please sign up or login with your details

Forgot password? Click here to reset