HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Empirical Bernstein stopping

Volodymyr Mnih 1 Csaba Szepesvari 1 Jean-Yves Audibert 2, 3, 4, 5
3 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
4 imagine [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech, LIGM - Laboratoire d'Informatique Gaspard-Monge
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

Contributor : Pascal Monasse Connect in order to contact the contributor
Submitted on : Tuesday, June 18, 2013 - 2:46:49 PM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Thursday, September 19, 2013 - 4:08:00 AM


Files produced by the author(s)



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⟩



Record views


Files downloads