Sparse least squares support vector machine with L0-norm in primal space
Qi Li, Xiaohang Li, Wei Ba · 2015
Least squares support vector machine (LS-SVM) has been successfully applied in many classification and regression tasks. The main drawback of the LS-SVM algorithm is the lack of sparseness. Combing the primal least squares twin support vector machine (LS-TSVM) and the sparse LS-SVM with L0-norm minimization, a new sparse least squares support vector regression algorithm with L0-norm in primal space(L0-PLSSVR) is proposed in this paper. Experiments on the artificial dataset illustrate that the novel L0-PLSSVR algorithm achieves better sparseness and generalization performance than the SVM and LS-SVM algorithm.