<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Bound-constrained Support Vector Machine(SVM) is one of the stateof- art model for binary classification. The decomposition method is currently one of the major methods for training SVMs, especially when the nonlinear kernel is used. In this paper, we proposed two new decomposition algorithms for training bound-constrained SVMs. Projected gradient algorithm and interior point method are combined together to solve the quadratic subproblem effciently. The main difference between the two algorithms is the way of choosing working set. The first one only uses first order derivative information of the model for simplicity. The second one incorporate part of second order information into the process of working set selection, besides the gradient. Both algorithms are proved to be global convergent in theory. New algorithms is compared with the famous package BSVM. Numerical experiments on several public data sets validate the effciency of the proposed methods.</p></abstract>

Bound-constrained Support Vector Machine(SVM) is one of the stateof- art model for binary classification. The decomposition method is currently one of the major methods for training SVMs, especially when the nonlinear kernel is used. In this paper, we proposed two new decomposition algorithms for training bound-constrained SVMs. Projected gradient algorithm and interior point method are combined together to solve the quadratic subproblem effciently. The main difference between the two algorithms is the way of choosing working set. The first one only uses first order derivative information of the model for simplicity. The second one incorporate part of second order information into the process of working set selection, besides the gradient. Both algorithms are proved to be global convergent in theory. New algorithms is compared with the famous package BSVM. Numerical experiments on several public data sets validate the effciency of the proposed methods.

Two New Decomposition Algorithms for Training Bound-Constrained Support Vector Machines*

Research Center on Fictitious Economy & Data Science, University of Chinese Academy of Sciences, Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China

Foundations of Computing and Decision Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Bound-constrained Support Vector Machine(SVM) is one of the stateof- art model for binary classification. The decomposition method is currently one of the...

Two New Decomposition Algorithms for Training Bound-Constrained Support Vector Machines*

Publié en ligne: 01 mars 2015

Pages: 67 - 86

DOI: https://doi.org/10.1515/fcds-2015-0005

Mots clés
decomposition algorithm, support vector machine, quadratic programming, global convergence

© 2015 Lingfeng Niu et. al.

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Two New Decomposition Algorithms for Training Bound-Constrained Support Vector Machines*

Publié en ligne: 01 mars 2015

Pages: 67 - 86

DOI: https://doi.org/10.1515/fcds-2015-0005

Mots clésdecomposition algorithm, support vector machine, quadratic programming, global convergence

© 2015 Lingfeng Niu et. al.

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
decomposition algorithm, support vector machine, quadratic programming, global convergence