Title :
Speeding up the IRWLS convergence to the SVM solution
Author :
Pérez-Cruz, Fernando ; Artés-Rodíguez, Antonio
Author_Institution :
Gatsby Comput. Neuroscience Unit, Univ. Coll. London, UK
Abstract :
We present the convergence demonstration of the iterative re-weighted least squares (IRWLS) procedure to the SVM solution, to propose two modifications, which significantly reduces the runtime complexity of the IRWLS. We show by means of computer experiments that the convergence can be speed up between two and eight times compare to the standard IRWLS procedure.
Keywords :
convergence of numerical methods; iterative methods; least squares approximations; support vector machines; SVM solution; computer experiments; convergence; iterative reweighted least squares procedure; runtime complexity; support vector machine; Convergence; Educational institutions; Lagrangian functions; Least squares approximation; Least squares methods; Quadratic programming; Runtime; Static VAr compensators; Support vector machine classification; Support vector machines;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1379969
