New Support Vector Algorithms

Abstract

We describe a new class of Support Vector algorithms for regression and classi cation In these algorithms a parameter lets one e ectively con trol the number of Support Vectors While this can be useful in its own right the parametrization has the additional bene t 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 classi cation case We describe the algorithms give some theoretical results concerning the meaning and the choice of and report experimental results

DOI: 10.1162/089976600300015565

Extracted Key Phrases

1 Figure or Table

050100150'00'02'04'06'08'10'12'14'16
Citations per Year

1,977 Citations

Semantic Scholar estimates that this publication has 1,977 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Schlkopf2000NewSV, title={New Support Vector Algorithms}, author={Bernhard Sch{\"{o}lkopf and Alexander J. Smola and Robert C. Williamson and Peter L. Bartlett}, journal={Neural Computation}, year={2000}, volume={12}, pages={1207-1245} }