On the Convergence Rate of Kernel-Based Sequential Greedy Regression

On the Convergence Rate of Kernel-Based Sequential Greedy Regression

A kernel-based greedy algorithm is presented to realize efficient sparse learning with data-dependent basis functions. Upper bound of generalization error is obtained based on complexity measure of hypothesis space with covering numbers. A careful analysis shows the error has a satisfactory decay ra...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Abstract and Applied Analysis 2012-01, Vol.2012 (1), p.1199-1207-477
Hauptverfasser: Wang, Xiaoyin, Wei, Xiaoyan, Pan, Zhibin
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Convergence
Hypotheses
Regularization methods
Studies
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A kernel-based greedy algorithm is presented to realize efficient sparse learning with data-dependent basis functions. Upper bound of generalization error is obtained based on complexity measure of hypothesis space with covering numbers. A careful analysis shows the error has a satisfactory decay rate under mild conditions.
ISSN:1085-3375
1687-0409
DOI:10.1155/2012/619138