Learning rates of regularized regression for functional data

Yong Li Xu; Di Rong Chen

doi:10.1142/S0219691309003288

Learning rates of regularized regression for functional data

Yong Li Xu^*
, Di Rong Chen

^*Corresponding author for this work

School of Mathematical Sciences

Beihang University

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

The study of regularized learning algorithms is a very important issue and functional data analysis extends classical methods. We establish the learning rates of the least square regularized regression algorithm in reproducing kernel Hilbert space for functional data. With the iteration method, we obtain fast learning rate for functional data. Our result is a natural extension for least square regularized regression algorithm when the dimension of input data is finite.

Original language	English
Pages (from-to)	839-850
Number of pages	12
Journal	International Journal of Wavelets, Multiresolution and Information Processing
Volume	7
Issue number	6
DOIs	https://doi.org/10.1142/S0219691309003288
State	Published - Nov 2009

Keywords

Functional data analysis
Learning theory
Regularized learning algorithm
Reproducing kernel Hilbert space

Access to Document

10.1142/S0219691309003288

Cite this

@article{fb922666c4cf4d44891a95dcd534895d,

title = "Learning rates of regularized regression for functional data",

abstract = "The study of regularized learning algorithms is a very important issue and functional data analysis extends classical methods. We establish the learning rates of the least square regularized regression algorithm in reproducing kernel Hilbert space for functional data. With the iteration method, we obtain fast learning rate for functional data. Our result is a natural extension for least square regularized regression algorithm when the dimension of input data is finite.",

keywords = "Functional data analysis, Learning theory, Regularized learning algorithm, Reproducing kernel Hilbert space",

author = "Xu, \{Yong Li\} and Chen, \{Di Rong\}",

year = "2009",

month = nov,

doi = "10.1142/S0219691309003288",

language = "英语",

volume = "7",

pages = "839--850",

journal = "International Journal of Wavelets, Multiresolution and Information Processing",

issn = "0219-6913",

publisher = "World Scientific Publishing Co. Pte Ltd",

number = "6",

}

TY - JOUR

T1 - Learning rates of regularized regression for functional data

AU - Xu, Yong Li

AU - Chen, Di Rong

PY - 2009/11

Y1 - 2009/11

N2 - The study of regularized learning algorithms is a very important issue and functional data analysis extends classical methods. We establish the learning rates of the least square regularized regression algorithm in reproducing kernel Hilbert space for functional data. With the iteration method, we obtain fast learning rate for functional data. Our result is a natural extension for least square regularized regression algorithm when the dimension of input data is finite.

AB - The study of regularized learning algorithms is a very important issue and functional data analysis extends classical methods. We establish the learning rates of the least square regularized regression algorithm in reproducing kernel Hilbert space for functional data. With the iteration method, we obtain fast learning rate for functional data. Our result is a natural extension for least square regularized regression algorithm when the dimension of input data is finite.

KW - Functional data analysis

KW - Learning theory

KW - Regularized learning algorithm

KW - Reproducing kernel Hilbert space

UR - https://www.scopus.com/pages/publications/76449095075

U2 - 10.1142/S0219691309003288

DO - 10.1142/S0219691309003288

M3 - 文章

AN - SCOPUS:76449095075

SN - 0219-6913

VL - 7

SP - 839

EP - 850

JO - International Journal of Wavelets, Multiresolution and Information Processing

JF - International Journal of Wavelets, Multiresolution and Information Processing

IS - 6

ER -

Learning rates of regularized regression for functional data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this