Sharp Analysis of Learning with Discrete Losses - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Sharp Analysis of Learning with Discrete Losses

Résumé

The problem of devising learning strategies for discrete losses (e.g., multilabeling, ranking) is currently addressed with methods and theoretical analyses ad-hoc for each loss. In this paper we study a least-squares framework to systematically design learning algorithms for discrete losses, with quantitative characterizations in terms of statistical and computational complexity. In particular we improve existing results by providing explicit dependence on the number of labels for a wide class of losses and faster learning rates in conditions of low-noise. Theoretical results are complemented with experiments on real datasets, showing the effectiveness of the proposed general approach.
Fichier principal
Vignette du fichier
sharp_main.pdf (265.46 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01893006 , version 1 (15-10-2018)

Identifiants

Citer

Alex Nowak-Vila, Francis Bach, Alessandro Rudi. Sharp Analysis of Learning with Discrete Losses. 2018. ⟨hal-01893006⟩
222 Consultations
214 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More