Journal
JOURNAL OF MACHINE LEARNING RESEARCH
Volume 22, Issue -, Pages 1-45Publisher
MICROTOME PUBL
Keywords
Generative Adversarial Networks; Wasserstein distances; deep learning theory; Lipschitz functions; trade-off properties
Ask authors/readers for more resources
This paper presents theoretical advances in WGANs, including discussions on architecture definition, mathematical features, and optimization properties. These features are verified through experiments to illustrate the trade-off effects between the generator and the discriminator.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available