Generalization performance of multi-class discriminant models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2000

Generalization performance of multi-class discriminant models

Hélène Paugam-Moisy
  • Function : Author
André Elisseeff
  • Function : Author
Yann Guermeur
  • Function : Author
  • PersonId : 830806


Starting from a direct definition of the notion of margin in the multiclass case , we study the generalization performance of multiclass discriminant systems. In the framework of statistical learning theory, we establish on this performance a bound based on covering numbers. An application to a linear ensemble method w hich estimates the class posterior probabilities provides us with a way to compa re this bound and another one based on combinatorial dimensions, with respect to the capacity measure they incorporate. Experimental results highlight their use fulness for a real-world problem.
No file

Dates and versions

inria-00099163 , version 1 (26-09-2006)


  • HAL Id : inria-00099163 , version 1


Hélène Paugam-Moisy, André Elisseeff, Yann Guermeur. Generalization performance of multi-class discriminant models. IJCNN'2000, 2000, Come, Italie, pp.177-182. ⟨inria-00099163⟩
47 View
0 Download


Gmail Facebook X LinkedIn More