Optimism in Active Learning with Gaussian Processes

Timothé Collet 1, 2 Olivier Pietquin 3, 4, 5
2 MALIS - MAchine Learning and Interactive Systems
SUPELEC-Campus Metz, CentraleSupélec
3 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : In the context of Active Learning for classification, the classification error depends on the joint distribution of samples and their labels which is initially unknown. The minimization of this error requires estimating this distribution. Online estimation of this distribution involves a trade-off between exploration and exploitation. This is a common problem in machine learning for which multi-armed bandit theory, building upon Optimism in the Face of Uncertainty, has been proven very efficient these last years. We introduce two novel algorithms that use Optimism in the Face of Uncertainty along with Gaussian Processes for the Active Learning problem. The evaluation lead on real world datasets shows that these new algorithms compare positively to state-of-the-art methods.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-01225826
Contributor : Olivier Pietquin <>
Submitted on : Friday, November 6, 2015 - 6:10:15 PM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Long-term archiving on : Monday, February 8, 2016 - 1:02:06 PM

File

ICONIP_2015_TCOP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01225826, version 1

Citation

Timothé Collet, Olivier Pietquin. Optimism in Active Learning with Gaussian Processes. 22nd International Conference on Neural Information Processing (ICONIP2015), Nov 2015, Istanbul, Turkey. ⟨hal-01225826⟩

Share

Metrics

Record views

373

Files downloads

426