Christmann, AndreasLuebke, KarstenMarin-Galiano, MarcosRüping, Stefan2005-11-072005-11-072005-11-07http://hdl.handle.net/2003/2166710.17877/DE290R-14494We investigate methods to determine appropriate choices of the hyper-parameters for kernel based methods. Support vector classification, kernel logistic regression and support vector regression are considered. Grid search, Nelder-Mead algorithm and pattern search algorithm are used.enconvex risk minimizationkernel logistic regressionstatistical machine learningsupport vector machinesupport vector regression004report