Concentration estimates for learning with unbounded sampling

Zheng-Chu Guo; Ding-Xuan Zhou

doi:10.1007/s10444-011-9238-8

Concentration estimates for learning with unbounded sampling

Zheng-Chu Guo, Ding-Xuan Zhou

Department of Mathematics

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

41 Citations (Scopus)

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.

Original language	English
Pages (from-to)	207-223
Journal	Advances in Computational Mathematics
Volume	38
Issue number	1
Online published	11 Oct 2011
DOIs	https://doi.org/10.1007/s10444-011-9238-8
Publication status	Published - Jan 2013

Research Keywords

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

Access Output

10.1007/s10444-011-9238-8

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{190c89f392014897ba5e4b8e0852ea78,

title = "Concentration estimates for learning with unbounded sampling",

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. {\textcopyright} 2011 Springer Science+Business Media, LLC.",

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

author = "Zheng-Chu Guo and Ding-Xuan Zhou",

year = "2013",

month = jan,

doi = "10.1007/s10444-011-9238-8",

language = "English",

volume = "38",

pages = "207--223",

journal = "Advances in Computational Mathematics",

issn = "1019-7168",

publisher = "Springer Netherlands",

number = "1",

}

TY - JOUR

T1 - Concentration estimates for learning with unbounded sampling

AU - Guo, Zheng-Chu

AU - Zhou, Ding-Xuan

PY - 2013/1

Y1 - 2013/1

N2 - 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.

AB - 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.

KW - Concentration estimates

KW - Empirical covering number

KW - Learning theory

KW - Least-square regression

KW - Regularization in reproducing kernel Hilbert spaces

UR - http://www.scopus.com/inward/record.url?scp=84873140485&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84873140485&origin=recordpage

U2 - 10.1007/s10444-011-9238-8

DO - 10.1007/s10444-011-9238-8

M3 - RGC 21 - Publication in refereed journal

SN - 1019-7168

VL - 38

SP - 207

EP - 223

JO - Advances in Computational Mathematics

JF - Advances in Computational Mathematics

IS - 1

ER -

Concentration estimates for learning with unbounded sampling

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this