Bounds on Error Expectation for Support Vector Machines

Top Cited Papers

1 September 2000

journal article
Published by MIT Press in Neural Computation

Vol. 12 (9) , 2013-2036
https://doi.org/10.1162/089976600300015042

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).

Keywords

MODEL SELECTION
TEST ERROR
GENERALIZATION ABILITY
NEW GEOMETRICAL CONCEPT
SUPPORT VECTOR
SUPPORT VECTOR MACHINE
SMALLEST SPHERE
ERROR EXPECTATION
DIRECT APPLICATION
OPTIMAL PARAMETER
PREVIOUS BOUND
SUPPORT VECTOR MACHINES

This publication has 1 reference indexed in Scilit:

Structural risk minimization over data-dependent hierarchies
IEEE Transactions on Information Theory, 1998