Smola, Bartlett, Scholkopf, and Schuurmans: Advances in Large Margin Classifiers 1999/07/09 12:27 2 Bounds on Error Expectation for Support Vector Machines
|
Abstract:
We introduce the concept of span of support vectors (SV) and show that the generalization ability of support vector machines (SVM) depends on this new geometrical concept. We prove that the value of the span is always smaller (and can be much smaller) than the diameter of the smallest sphere containing the support vectors, used in previous bounds (Vapnik, 1998). We also demonstate experimentally that the prediction of the test error given by the span is very accurate and has direct application in model selection (choice of the optimal parameters of the SVM) Recently, a new type of algorithm with a high level of performance called Support Vector Machines (SVM) has been introduced (Boser et al., 1992; Vapnik, 1995). Usually, the good generalization ability of SVM is explained by the existence
Citations
| 4514 | Statistical Learning Theory – Vapnik - 1998 |
| 688 | A training algorithm for optimal margin classifiers – Boser, Guyon, et al. - 1992 |
| 208 | Structural risk minimization over data-dependent hierarchies – Shawe-Taylor, Bartlett, et al. - 1996 |
| 85 | Shawe-Taylor: Generalization Performance of Support Vector Machines and other Pattern Classifiers – Bartlett, J - 1999 |
| 37 | On estimation of characters obtained in statistical procedure in re cognition. Technicheskaya Kibernetica (in Russian – Lunts, Brailovsky - 1969 |
| 19 | Generalization bounds via eigenvalues of the Gram matrix – Scholkopf, Shawe-Taylor, et al. - 1999 |
