Some Theoretical Insights into Wasserstein GANs - Sorbonne Université
Journal Articles Journal of Machine Learning Research Year : 2021

Some Theoretical Insights into Wasserstein GANs

Abstract

Generative Adversarial Networks (GANs) have been successful in producing outstanding results in areas as diverse as image, video, and text generation. Building on these successes, a large number of empirical studies have validated the benefits of the cousin approach called Wasserstein GANs (WGANs), which brings stabilization in the training process. In the present paper, we add a new stone to the edifice by proposing some theoretical advances in the properties of WGANs. First, we properly define the architecture of WGANs in the context of integral probability metrics parameterized by neural networks and highlight some of their basic mathematical features. We stress in particular interesting optimization properties arising from the use of a parametric 1-Lipschitz discriminator. Then, in a statistically-driven approach, we study the convergence of empirical WGANs as the sample size tends to infinity, and clarify the adversarial effects of the generator and the discriminator by underlining some trade-off properties. These features are finally illustrated with experiments using both synthetic and real-world datasets.
Fichier principal
Vignette du fichier
jmlr2021.pdf (4.13 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02751784 , version 1 (03-06-2020)
hal-02751784 , version 2 (28-05-2021)
hal-02751784 , version 3 (04-06-2021)
hal-02751784 , version 4 (08-06-2021)

Identifiers

  • HAL Id : hal-02751784 , version 2

Cite

Gérard Biau, Maxime Sangnier, Ugo Tanielian. Some Theoretical Insights into Wasserstein GANs. Journal of Machine Learning Research, 2021. ⟨hal-02751784v2⟩
227 View
190 Download

Share

More