L1-norm least squares support vector regression via the alternating direction method of multipliers

被引：5

作者：

Ye Y.-F. ^{[1
,2
]}

Ying C. ^{[3
]}

Jiang Y.-X. ^{[1
]}

Li C.-N. ^{[2
]}

机构：

[1] College of Economics, Zhejiang University, Hangzhou

[2] Zhijiang College, Zhejiang University of Technology, Hangzhou

[3] Rainbow City Primary School, Hangzhou

来源：

Journal of Advanced Computational Intelligence and Intelligent Informatics | 2017年 / 21卷 / 06期

基金：

中国博士后科学基金; 中国国家自然科学基金;

关键词：

ADMM; Feature selection; L1-norm; Least squares; Support vector regression;

D O I：

10.20965/jaciii.2017.p1017

中图分类号：

学科分类号：

摘要：

In this study, we focus on the feature selection problem in regression, and propose a new version of L1 support vector regression (L1-SVR), known as L1-norm least squares support vector regression (L1-LSSVR). The alternating direction method of multipliers (ADMM), a method from the augmented Lagrangian family, is used to solve L1-LSSVR. The sparse solution of L1- LSSVR can realize feature selection effectively. Furthermore, L1-LSSVR is decomposed into a sequence of simpler problems by the ADMM algorithm, resulting in faster training speed. The experimental results demonstrate that L1-LSSVR is not only as effective as L1-SVR, LSSVR, and SVR in both feature selection and regression, but also much faster than L1-SVR and SVR.

引用

页码：1017 / 1025

页数：8

共 23 条

[1] Drucker H., Burges C.J.C., Kaufman L., Smola A., Vapnik V., Support vector regression machines, Advances in Neural Information Processing Systems, 9, (1997)
[2] Burges C., A tutorial on support vector machines for pattern recognition, Data Min. Knowl. Discov., 2, pp. 121-167, (1998)
[3] Bi J., Bennett K.P., A geometric approach to support vector regression, Neurocomputing, 55, 1-2, pp. 79-108, (2003)
[4] Smola A., Scholkopf B., A tutorial on support vector regression, Statistic Computing, 14, 3, pp. 199-222, (2004)
[5] Huang C.L., Tsai C.Y., A hybrid SOFM-SVR with a filterbased feature selection for stock market forecasting, Expert Systems with Application, 36, pp. 1529-1539, (2009)
[6] Yang J.B., Ong C.J., Feature selection using probabilistic prediction of support vector regression, IEEE Trans. on Neural Networks, 22, pp. 954-962, (2011)
[7] Ye Y.F., Cao H., Bai L., Wang Z., Shao Y.H., Exploring determinants of inflation in China based on L1-?-twin support vector regression, Procedia Computer Science, 17, pp. 514-522, (2013)
[8] Peng X., Xu D., A local information-based feature-selection algorithm for data regression, Pattern Recognition, 46, pp. 2519-2530, (2013)
[9] Ye Y.F., Jiang Y.X., Shao Y.H., Li C.N., Financial conditions index construction through weighted lp-norm support vector regression, J. Adv. Comput. Intell. Intell. Inform., 19, pp. 397-406, (2015)
[10] Ye Y.F., Shao Y.H., Li C.N., Wavelet lp-norm support vector regression with feature selection, J. Adv. Comput. Intell. Intell. Inform., 19, pp. 407-416, (2015)

← 1 2 3 →