Linear Convergence of a Decomposition Method for Support Vector Machines

Recently the asymptotic convergence of some commonly used decomposition methods for support vector machines has been established. However, their local convergence rates are still unknown. In this paper, under the assumptions that the kernel matrix is positive definite and the problem is non-degenerate, we prove the linear convergence of a popular decomposition method.

[1]  P. Tseng,et al.  On the convergence of the coordinate descent method for convex differentiable minimization , 1992 .

[2]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[4]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[5]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[6]  Chih-Jen Lin,et al.  The analysis of decomposition methods for support vector machines , 2000, IEEE Trans. Neural Networks Learn. Syst..

[7]  Chih-Jen Lin,et al.  On the convergence of the decomposition method for support vector machines , 2001, IEEE Trans. Neural Networks.

[8]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[9]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[10]  Chih-Jen Lin,et al.  A formal analysis of stopping criteria of decomposition methods for support vector machines , 2002, IEEE Trans. Neural Networks.

[11]  Chih-Jen Lin,et al.  Asymptotic convergence of an SMO algorithm without any assumptions , 2002, IEEE Trans. Neural Networks.

[12]  Chih-Jen Lin,et al.  Decomposition Methods for Linear Support Vector Machines , 2003, Neural Computation.