New Support Vector Algorithms
We describe a new class of Support Vector algorithms for regression and classiication. In these algorithms, a parameter lets one eectively control the number of Support Vectors. While this can be useful in its own right, the parametrization has the additional beneet of enabling us to eliminate one of the other free parameters of the algorithm: the accuracy parameter " in the regression case, and the regularization constant C in the classiication case. We describe the algorithms, give some theoretical results concerning the meaning and the choice of , and report experimental results.