Risk bounds for model selection via penalization

Performance bounds for criteria for model selection are developed using recent theory for sieves. The model selection criteria are based on an empirical loss or contrast function with an added penalty term motivated by empirical process theory and roughly proportional to the number of parameters nee...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Probability theory and related fields 1999-02, Vol.113 (3), p.301-413
Hauptverfasser:	BARRON, A, BIRGE, L, MASSART, P
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Approximation Criteria Density Estimation Exact sciences and technology Linear inference, regression Mathematical models Mathematics Minimax technique Neural networks Parameters Parametric inference Polynomials Probability Probability and statistics Sciences and techniques of general use Smoothness Statistics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!