Data-driven probability concentration and sampling on manifold

A new methodology is proposed for generating realizations of a random vector with values in a finite-dimensional Euclidean space that are statistically consistent with a dataset of observations of this vector. The probability distribution of this random vector, while a priori not known, is presumed...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of computational physics 2016-09, Vol.321 (C), p.242-258
Hauptverfasser:	Soize, C., Ghanem, R.
Format:	Artikel
Sprache:	eng
Schlagworte:	Concentration of probability Design of experiments for random parameters Diffusion maps Engineering Sciences Mathematics MCMC generator Measure concentration Probability Probability distribution on manifolds Random sampling generator Statistics Statistics on manifolds
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!