Volume no :5, Issue no: 2, December (2016)

International Journal of Applied Mathematics and Machine Learning

FAST M-TLS-RSVR AND FOR MULTI-OUTPUT REGRESSION

Author's: Chunhui Zhao and Liya Fan
Pages: [141] - [157]
Received Date: December 29, 2016
Submitted by: Jianqiang Gao.
DOI: http://dx.doi.org/10.18642/ijamml_7100121756

Abstract

This paper focuses on research multi-output regression problems and proposes two novel fast learning algorithms named as fast multi-output twin least squares regularized SVR (FM-TLS-RSVR) and fast multi-output least squares respectively. The main advantage of the proposed methods is to consider the cross relations among output vectors as a whole and avoid the singularity of matrices. In addition, the proposed FM-TLS-RSVR also possesses the sparsity. Experiment results indicate that FM-TLS-RSVR and are two effective and competitive multi-output regressors.

Keywords

multi-output regression problem, least-squares technique, support vector machine, KKT conditions, regression accuracy.