Bounding the Capacity Measure of Multi-Class Discriminant Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 2002

Bounding the Capacity Measure of Multi-Class Discriminant Models

Yann Guermeur
  • Function : Author
  • PersonId : 830806
André Elisseeff
  • Function : Author
Dominique Zelus
  • Function : Author

Abstract

Vapnik's statistical learning theory has mainly been developed for two types of problems: pattern recognition (computation of dichotomies) and regression (estimation of real-valued functions). Multi-class discriminant analysis has only been studied independently in recent years. Extending several standard results, among which a famous theorem by Bartlett, we have derived distribution-free uniform strong laws of large numbers devoted to multi-class discriminant models. This technical report deals with the computation of the capacity measures involved in these bounds on the expected risk. It considers more specifically the case of multi-class SVMs.
Not file

Dates and versions

inria-00100733 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100733 , version 1

Cite

Yann Guermeur, André Elisseeff, Dominique Zelus. Bounding the Capacity Measure of Multi-Class Discriminant Models. [Intern report] A02-R-028 || guermeur02b, 2002, 20 p. ⟨inria-00100733⟩
60 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More