To minimize the primal support vector machine (SVM) problem, we propose to use iterative majorization. To do so, we propose to use it- erative majorization. To allow for nonlinearity of the predictors, we use (non)monotone spline transformations. An advantage over the usual ker- nel approach in the dual problem is that the variables can be easily inter- preted. We illustrate this with an example from the literature.

Additional Metadata
Keywords I-Splines, iterative majorization, support vector machines
Persistent URL hdl.handle.net/1765/7889
Series Econometric Institute Research Papers
Journal Report / Econometric Institute, Erasmus University Rotterdam
Citation
Groenen, P.J.F, Bioch, J.C, & Nalbantov, G.I. (2006). Nonlinear support vector machines through iterative majorization and I-splines (No. EI 2006-25). Report / Econometric Institute, Erasmus University Rotterdam. Retrieved from http://hdl.handle.net/1765/7889