Concentration estimates for learning with unbounded sampling

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

37 Scopus Citations
Scopus Metrics
View graph of relations

Author(s)

  • Zheng-Chu Guo
  • Ding-Xuan Zhou

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)207-223
Journal / PublicationAdvances in Computational Mathematics
Volume38
Issue number1
Online published11 Oct 2011
Publication statusPublished - Jan 2013

Link(s)

DOI

DOI
Check@CityULib
Link to Scopus https://www.scopus.com/record/display.uri?eid=2-s2.0-84873140485&origin=recordpage
Permanent Link https://scholars.cityu.edu.hk/en/publications/publication(190c89f3-9201-4897-ba5e-4b8e0852ea78).html

Abstract

The least-square regression problem is considered by regularization schemes in reproducing kernel Hilbert spaces. The learning algorithm is implemented with samples drawn from unbounded sampling processes. The purpose of this paper is to present concentration estimates for the error based on ℓ2-empirical covering numbers, which improves learning rates in the literature. © 2011 Springer Science+Business Media, LLC.

Research Area(s)

  • Concentration estimates, Empirical covering number, Learning theory, Least-square regression, Regularization in reproducing kernel Hilbert spaces

Fingerprint

Publication fingerprints text

100
learning INIS
100
concentration INIS
100
sampling INIS
100
Sample Mathematics
100
Least Square Mathematics
100
Hilbert Space Mathematics
100
Regularization Mathematics
100
Covering Number Mathematics
100
Square Regression Mathematics
100
Algorithm Mathematics
Full Fingerprint ›

Citation Format(s)

[ RIS ] [ BibTeX ]
Concentration estimates for learning with unbounded sampling. / Guo, Zheng-Chu; Zhou, Ding-Xuan.
In: Advances in Computational Mathematics, Vol. 38, No. 1, 01.2013, p. 207-223.

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review