DeepAI AI Chat
Log In Sign Up

A Convenient Infinite Dimensional Framework for Generative Adversarial Learning

by   Hayk Asatryan, et al.
Bergische Universität Wuppertal

In recent years, generative adversarial networks (GANs) have demonstrated impressive experimental results while there are only a few works that foster statistical learning theory for GANs. In this work, we propose an infinite dimensional theoretical framework for generative adversarial learning. Assuming the class of uniformly bounded k-times α-Hölder differentiable and uniformly positive densities, we show that the Rosenblatt transformation induces an optimal generator, which is realizable in the hypothesis space of α-Hölder differentiable generators. With a consistent definition of the hypothesis space of discriminators, we further show that in our framework the Jensen-Shannon divergence between the distribution induced by the generator from the adversarial learning procedure and the data generating distribution converges to zero. Under sufficiently strict regularity assumptions on the density of the data generating process, we also provide rates of convergence based on concentration and chaining.


page 1

page 2

page 3

page 4


The Inductive Bias of Restricted f-GANs

Generative adversarial networks are a novel method for statistical infer...

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling

Generative modeling of high dimensional data like images is a notoriousl...

Rates of convergence for density estimation with GANs

We undertake a precise study of the non-asymptotic properties of vanilla...

Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training

Generative Adversarial Networks (GANs) have become a widely popular fram...

Statistical Guarantees of Generative Adversarial Networks for Distribution Estimation

Generative Adversarial Networks (GANs) have achieved great success in un...

Evaluating a Generative Adversarial Framework for Information Retrieval

Recent advances in Generative Adversarial Networks (GANs) have resulted ...

Partition-Guided GANs

Despite the success of Generative Adversarial Networks (GANs), their tra...