Jimenez, F.
, Koepke, A.
, Gregg, M.
and Frey, M.
(2021),
Generative Adversarial Network Performance in Low-Dimensional Settings, Journal of Research (NIST JRES), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://dx.doi.org/10.6028/jres.126.008, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=930944
(Accessed December 3, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Generative Adversarial Network Performance in Low-Dimensional Settings
Published
Author(s)
, , ,
Abstract
A generative adversarial network (GAN) is an artificial neural network with a distinctive training architecture, designed to create examples that faithfully reproduce a target distribution. GANs have recently had particular success in applications involving high-dimensional distributions in areas such as image processing. Little work has been reported for low dimensions, where properties of GANs may be better identified and understood. We studied GAN performance in simulated low-dimensional settings, allowing us to transparently assess effects of target distribution complexity and training data sample size on GAN performance in a simple experiment. This experiment revealed two important forms of GAN error, tail underfilling and bridge bias, where the latter is analogous to the tunneling observed in high-dimensional GANs.Citation
Journal of Research (NIST JRES) -
Volume
126
NIST Pub Series
Pub Type
NIST Pubs
Download Paper
Keywords
earth mover distance, experiment protocol, generative adversarial network, mode tunneling, modeling error, target distribution complexity
Citation
Issues
If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.
Created April 20, 2021