Optimal regularization parameters selection for laplacian support vector machine

Juntao Li; Yingmin Jia; Junping Du; Wenlin Li

doi:10.1109/CHICC.2008.4605084

Optimal regularization parameters selection for laplacian support vector machine

Juntao Li^*
, Yingmin Jia
, Junping Du
, Wenlin Li

^*Corresponding author for this work

School of Automation Science and Electrical Engineering

Beihang University
Beijing University of Posts and Telecommunications
Henan Normal University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Laplacian support vector machine (LapSVM) is an attracting tool for semi-supervised classification with manifold regularization. In this paper, we devote to selecting the extrinsic and intrinsic regularization parameters. To this end, a fusion of training and validation levels is first proposed, based on which, the optimal regularization parameters selection problem can be cast as a standard semidefinite programming. Then, a hybrid manifold regularization algorithm is also developed, thus eliminating the difficulty of balancing between the ambient space and the intrinsic geometric of the data distribution. Finally, experiments are performed that verify the research results.

Original language	English
Title of host publication	Proceedings of the 27th Chinese Control Conference, CCC
Pages	464-468
Number of pages	5
DOIs	https://doi.org/10.1109/CHICC.2008.4605084
State	Published - 2008
Event	27th Chinese Control Conference, CCC - Kunming, Yunnan, China Duration: 16 Jul 2008 → 18 Jul 2008

Publication series

Name	Proceedings of the 27th Chinese Control Conference, CCC

Conference

Conference	27th Chinese Control Conference, CCC
Country/Territory	China
City	Kunming, Yunnan
Period	16/07/08 → 18/07/08

Keywords

Laplacian support vector machine
Manifold regularization
Semidefinite programming (SDP)

Access to Document

10.1109/CHICC.2008.4605084

Cite this

@inproceedings{6ce32d72c9024bd082f3b8ed854eb012,

title = "Optimal regularization parameters selection for laplacian support vector machine",

abstract = "Laplacian support vector machine (LapSVM) is an attracting tool for semi-supervised classification with manifold regularization. In this paper, we devote to selecting the extrinsic and intrinsic regularization parameters. To this end, a fusion of training and validation levels is first proposed, based on which, the optimal regularization parameters selection problem can be cast as a standard semidefinite programming. Then, a hybrid manifold regularization algorithm is also developed, thus eliminating the difficulty of balancing between the ambient space and the intrinsic geometric of the data distribution. Finally, experiments are performed that verify the research results.",

keywords = "Laplacian support vector machine, Manifold regularization, Semidefinite programming (SDP)",

author = "Juntao Li and Yingmin Jia and Junping Du and Wenlin Li",

year = "2008",

doi = "10.1109/CHICC.2008.4605084",

language = "英语",

isbn = "9787900719706",

series = "Proceedings of the 27th Chinese Control Conference, CCC",

pages = "464--468",

booktitle = "Proceedings of the 27th Chinese Control Conference, CCC",

note = "27th Chinese Control Conference, CCC ; Conference date: 16-07-2008 Through 18-07-2008",

}

Li, J, Jia, Y, Du, J & Li, W 2008, Optimal regularization parameters selection for laplacian support vector machine. in Proceedings of the 27th Chinese Control Conference, CCC., 4605084, Proceedings of the 27th Chinese Control Conference, CCC, pp. 464-468, 27th Chinese Control Conference, CCC, Kunming, Yunnan, China, 16/07/08. https://doi.org/10.1109/CHICC.2008.4605084

Optimal regularization parameters selection for laplacian support vector machine. / Li, Juntao; Jia, Yingmin; Du, Junping et al.
Proceedings of the 27th Chinese Control Conference, CCC. 2008. p. 464-468 4605084 (Proceedings of the 27th Chinese Control Conference, CCC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimal regularization parameters selection for laplacian support vector machine

AU - Li, Juntao

AU - Jia, Yingmin

AU - Du, Junping

AU - Li, Wenlin

PY - 2008

Y1 - 2008

N2 - Laplacian support vector machine (LapSVM) is an attracting tool for semi-supervised classification with manifold regularization. In this paper, we devote to selecting the extrinsic and intrinsic regularization parameters. To this end, a fusion of training and validation levels is first proposed, based on which, the optimal regularization parameters selection problem can be cast as a standard semidefinite programming. Then, a hybrid manifold regularization algorithm is also developed, thus eliminating the difficulty of balancing between the ambient space and the intrinsic geometric of the data distribution. Finally, experiments are performed that verify the research results.

AB - Laplacian support vector machine (LapSVM) is an attracting tool for semi-supervised classification with manifold regularization. In this paper, we devote to selecting the extrinsic and intrinsic regularization parameters. To this end, a fusion of training and validation levels is first proposed, based on which, the optimal regularization parameters selection problem can be cast as a standard semidefinite programming. Then, a hybrid manifold regularization algorithm is also developed, thus eliminating the difficulty of balancing between the ambient space and the intrinsic geometric of the data distribution. Finally, experiments are performed that verify the research results.

KW - Laplacian support vector machine

KW - Manifold regularization

KW - Semidefinite programming (SDP)

UR - https://www.scopus.com/pages/publications/52449098400

U2 - 10.1109/CHICC.2008.4605084

DO - 10.1109/CHICC.2008.4605084

M3 - 会议稿件

AN - SCOPUS:52449098400

SN - 9787900719706

T3 - Proceedings of the 27th Chinese Control Conference, CCC

SP - 464

EP - 468

BT - Proceedings of the 27th Chinese Control Conference, CCC

T2 - 27th Chinese Control Conference, CCC

Y2 - 16 July 2008 through 18 July 2008

ER -

Optimal regularization parameters selection for laplacian support vector machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this