Reducing the statistical error of generative adversarial networks using space‐filling sampling

This paper introduces a novel approach to reducing statistical errors in generative models, with a specific focus on generative adversarial networks (GANs). Inspired by the error analysis of GANs, we find that statistical errors mainly arise from random sampling, leading to significant uncertainties...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Stat (International Statistical Institute) 2024, Vol.13 (1), p.n/a
Hauptverfasser:	Wang, Sumin, Gao, Yuyou, Zhou, Yongdao, Pan, Bin, Xu, Xia, Li, Tao
Format:	Artikel
Sprache:	eng
Schlagworte:	distribution matching error analysis generative learning representative samples space‐filling design statistical errors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!