Capacity dependent estimations by integral operator techniques

Capacity dependent estimations by integral operator techniques

In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qin Guo, Yukui Zhu, Hongwei Sun
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Algorithm design and analysis
Approximation error
Educational institutions
Eigenvalues and eigenfunctions
Kernel
Least squares approximation
Sun
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -β/(1+2β) ) by integral operator techniques.
DOI:10.1109/CISP.2010.5648072