HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Margin error and generalization capabilities of multiclass discriminant systems

André Elisseeff 1 Yann Guermeur 2 Hélène Paugam-Moisy
2 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This technical report exposes an extension of a lemma by Bartlett to the multiclass case. First, discussing the notion of margin and how its use for biclass discriminant models, we introduce the notion of margin for the multiclass case. Then, we develop our calculations and prove how to derive generalization error bounds for classifiers having multiple outputs. These bounds are expressed in terms of covering numbers. This report shows how to bound these quantities for the set of functions we consider and give an example for linear discriminant systems.
Document type :
Complete list of metadata

Contributor : Publications Loria Connect in order to contact the contributor
Submitted on : Tuesday, September 26, 2006 - 8:53:00 AM
Last modification on : Friday, February 4, 2022 - 3:34:41 AM


  • HAL Id : inria-00099333, version 1



André Elisseeff, Yann Guermeur, Hélène Paugam-Moisy. Margin error and generalization capabilities of multiclass discriminant systems. [Intern report] A00-R-112 || elisseeff00b, 2000. ⟨inria-00099333⟩



Record views