We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the $V_gamma$ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7169 |
| Date | 01 May 2000 |
| Creators | Evgeniou, Theodoros, Pontil, Massimiliano |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 9 p., 1149066 bytes, 253797 bytes, application/postscript, application/pdf |
| Relation | AIM-1681, CBCL-184 |
Page generated in 0.0021 seconds