Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

被引：8

作者：

Guermeur, Yann ^{[1
]}

机构：

[1] LORIA, CNRS, F-54506 Vandoeuvre Les Nancy, France

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2010年 / 39卷 / 03期

关键词：

Generalized VC dimensions; Multi-class support vector machines; Rademacher complexity; Sample complexity; CLASSIFICATION;

D O I：

10.1080/03610920903140288

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such oVC dimensionso exist for models taking values in {0, 1}, [[1, Q]], and . We introduce the generalizations appropriate for the missing case, the one of models with values in Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.

引用

页码：543 / 557

页数：15

共 18 条

[1] Scale-sensitive dimensions, uniform convergence, and learnability [J].