Stability revisited: new generalisation bounds for the Leave-one-Out - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Stability revisited: new generalisation bounds for the Leave-one-Out

Résumé

The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion of $L^q$ stability, and the strong use of moment inequalities. $L^q$ stability extends the ongoing notion of hypothesis stability while remaining weaker than the uniform stability. It leads to new PAC exponential generalisation bounds for Leave-one-Out under mild assumptions. In the literature, such bounds are available only for uniform stable algorithms under boundedness for instance. Our generic strategy is applied to the Ridge regression algorithm as a first step.
Fichier principal
Vignette du fichier
main.pdf (270.64 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01355365 , version 1 (23-08-2016)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

  • HAL Id : hal-01355365 , version 1

Citer

Alain Celisse, Benjamin Guedj. Stability revisited: new generalisation bounds for the Leave-one-Out. 2016. ⟨hal-01355365⟩
474 Consultations
260 Téléchargements

Partager

Gmail Facebook X LinkedIn More