Sparse online learning with bandit feedback - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Sparse online learning with bandit feedback

Résumé

The bandit classification problem considers learning the labels of a time-indexed data stream under a mere " hit-or-miss " binary guiding. Adapting the OVA (" one-versus-all ") hinge loss setup, we develop a sparse and lightweight solution to this problem. The issued sequential norm-minimal update solves the classification problem in finite time in the separable case, provided enough redundancy is present in the data. An O(√ T) regret in moreover expected in the non-separable case. The algorithm shows effectiveness on both large scale text-mining and machine learning datasets, with (i) a favorable comparison with the more demanding confidence-based second-order bandits setups on large scale datasets and (ii) a good sparsity and efficacy when a kernel approach is applied to non-separable datasets.
Fichier principal
Vignette du fichier
MLJ-main (1).pdf (572.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01345825 , version 1 (15-07-2016)

Licence

Paternité

Identifiants

  • HAL Id : hal-01345825 , version 1

Citer

Hongliang Zhong, Emmanuel Daucé. Sparse online learning with bandit feedback. 2016. ⟨hal-01345825⟩
247 Consultations
262 Téléchargements

Partager

Gmail Facebook X LinkedIn More