Schoelkopf, BernhardSmola, AlexanderWilliamson, RobertBartlett, Peter2015-12-132015-12-130899-7667http://hdl.handle.net/1885/88973We propose a new class of support vector algorithms for regression and classification. In these algorithms, a parameter ν lets one effectively control the number of support vectors. While this can be useful in its own right, the parameterization has the20002015-12-12