L p -norm Sauer-Shelah Lemma for Margin Multi-category Classifiers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Computer and System Sciences Year : 2017

L p -norm Sauer-Shelah Lemma for Margin Multi-category Classifiers


In the framework of agnostic learning, one of the main open problems of the theory of multi-category pattern classification is the characterization of the way the complexity varies with the number C of categories. More precisely, if the classifier is characterized only through minimal learnability hypotheses, then the optimal dependency on C that an upper bound on the probability of error should exhibit is unknown. We consider margin classifiers. They are based on classes of vector-valued functions with one component function per category, and the classes of component functions are uniform Glivenko-Cantelli classes. For these classifiers, an L p-norm Sauer-Shelah lemma is established. It is then used to derive guaranteed risks in the L ∞ and L 2-norms. These bounds improve over the state-of-the-art ones with respect to their dependency on C, which is sublinear.
Fichier principal
Vignette du fichier
guermeur16a.pdf (582.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01371331 , version 1 (25-09-2016)



Yann Guermeur. L p -norm Sauer-Shelah Lemma for Margin Multi-category Classifiers. Journal of Computer and System Sciences, 2017, 89, pp.450-473. ⟨10.1016/j.jcss.2017.06.003⟩. ⟨hal-01371331⟩
148 View
179 Download



Gmail Facebook Twitter LinkedIn More