On the almost optimality of blind active sampling.

Olivier Teytaud 1, 2
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : We show that blind active sampling is almost optimal in the case of large covering numbers in regression with finite precision. THIS IS A NON-COPYRIGHTED PUBLICATION IN A NATIONAL CONFERENCE.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00287874
Contributor : Olivier Teytaud <>
Submitted on : Friday, June 13, 2008 - 11:09:09 AM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM

Identifiers

  • HAL Id : inria-00287874, version 1

Collections

Citation

Olivier Teytaud. On the almost optimality of blind active sampling.. CAP 2008, May 2008, Porquerolles, France. ⟨inria-00287874⟩

Share

Metrics

Record views

273