Empirical Bernstein stopping - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Empirical Bernstein stopping

(1) , (1) , (2, 3, 4, 5)
1
2
3
4
5

Résumé

Sampling is a popular way of scaling up machine learning algorithms to large datasets. The question often is how many samples are needed. Adaptive stopping algorithms monitor the performance in an online fashion and they can stop early, saving valuable resources. We consider problems where probabilistic guarantees are desired and demonstrate how recently-introduced empirical Bernstein bounds can be used to design stopping rules that are efficient. We provide upper bounds on the sample complexity of the new rules, as well as empirical results on model selection and boosting in the filtering setting.
Fichier principal
Vignette du fichier
ICML08b.pdf (171.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00834983 , version 1 (18-06-2013)

Identifiants

Citer

Volodymyr Mnih, Csaba Szepesvari, Jean-Yves Audibert. Empirical Bernstein stopping. ICML '08 Proceedings of the 25th international conference on Machine learning, Jul 2008, Helsinki, Finland. pp.672-679, ⟨10.1145/1390156.1390241⟩. ⟨hal-00834983⟩
347 Consultations
583 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More