N. Ancona (1999)
Classification Properties of Support Vector Machines for Regression
Istituto Elaborazione Segnali ed Immagini, Bari, Italy.
In the same hypotheses of the Pontil's theorem, we show that the optimal approximating hyperplane solution of SVMR classifies the data. Moreover, the zero level curve of the solution of SVMR and the optimal separating hyperplane solution of SVMC coincide.