Bounds on error expectation for support vector machines

被引：608

作者：

Vapnik, V ^{[1
]}

Chapelle, O ^{[1
]}

机构：

[1] Ecole Normale Super Lyon, AT&T Labs Res, F-69364 Lyon, France

来源：

NEURAL COMPUTATION | 2000年 / 12卷 / 09期

关键词：

D O I：

10.1162/089976600300015042

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

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).

引用

页码：2013 / 2036

页数：24