Title :
Working Set Selection Using Functional Gain for LS-SVM
Author :
Bo, Liefeng ; Jiao, Licheng ; Wang, Ling
Author_Institution :
Xi- dian Univ., Xi´´an
Abstract :
The efficiency of sequential minimal optimization (SMO) depends strongly on the working set selection. This letter shows how the improvement of SMO in each iteration, named the functional gain (FG), is used to select the working set for least squares support vector machine (LS-SVM). We prove the convergence of the proposed method and give some theoretical support for its performance. Empirical comparisons demonstrate that our method is superior to the maximum violating pair (MVP) working set selection.
Keywords :
convergence of numerical methods; iterative methods; least squares approximations; optimisation; set theory; support vector machines; LS-SVM; convergence; functional gain; least squares support vector machine; sequential minimal optimization; working set selection; Character generation; Convergence; Fasteners; Gaussian processes; Kernel; Large-scale systems; Least squares methods; Quadratic programming; Support vector machine classification; Support vector machines; Fast algorithm; least squares support vector machine (LS-SVM); sequential minimal optimization (SMO); Algorithms; Artificial Intelligence; Computer Simulation; Models, Theoretical; Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2007.899715
