HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

Analyses on kernel-specific generalization ability for kernel regressors with training samples

Files in This Item:
ISSPIT2010_61-66.pdf100.53 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/46942

Title: Analyses on kernel-specific generalization ability for kernel regressors with training samples
Authors: Tanaka, Akira Browse this author →KAKEN DB
Miyakoshi, Masaaki Browse this author
Keywords: kernel regressor
reproducing kernel Hilbert space
generalization error
training samples
Issue Date: 15-Dec-2010
Publisher: IEEE
Journal Title: 2010 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)
Start Page: 61
End Page: 66
Publisher DOI: 10.1109/ISSPIT.2010.5711725
Abstract: Theoretical analyses on generalization error of a model space for kernel regressors with respect to training samples are given in this paper. In general, the distance between an unknown true function and a model space tends to be small with a larger set of training samples. However, it is not clarified that a larger set of training samples achieves a smaller difference at each point of the unknown true function and the orthogonal projection of it onto the model space, compared with a smaller set of training samples. In this paper, we show that the upper bound of the squared difference at each point of these two functions with a larger set of training samples is not larger than that with a smaller set of training samples. We also give some numerical examples to confirm our theoretical result.
Conference Name: 2010 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)
Conference Place: Luxor
Rights: © 2011 IEEE. Reprinted, with permission, from Tanaka, A., Miyakoshi, M., Analyses on kernel-specific generalization ability for kernel regressors with training samples, 2010 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Dec. 2010. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Hokkaido University products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.
Type: proceedings (author version)
URI: http://hdl.handle.net/2115/46942
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 田中 章

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 

 - Hokkaido University