Active Learning for Accurate Estimation of Linear Models

Carlos Riquelme 1 Mohammad Ghavamzadeh 2, 3 Alessandro Lazaric 2
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We explore the sequential decision-making problem where the goal is to estimate a number of linear models uniformly well, given a shared budget of random contexts independently sampled from a known distribution. For each incoming context, the decision-maker selects one of the linear models and receives an observation that is corrupted by the unknown noise level of that model. We present Trace-UCB, an adaptive allocation algorithm that learns the models' noise levels while balancing contexts accordingly across them, and prove bounds for its simple regret in both expectation and high-probability. We extend the algorithm and its bounds to the high dimensional setting , where the number of linear models times the dimension of the contexts is more than the total budget of samples. Simulations with real data suggest that Trace-UCB is remarkably robust , outperforming a number of baselines even when its assumptions are violated.
Type de document :
Communication dans un congrès
ICML 2017 - 34th International Conference on Machine Learning, Aug 2017, Sydney, Australia. pp.36
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01538762
Contributeur : Alessandro Lazaric <>
Soumis le : mercredi 14 juin 2017 - 10:14:58
Dernière modification le : mardi 3 juillet 2018 - 11:35:56
Document(s) archivé(s) le : mardi 12 décembre 2017 - 13:03:34

Fichier

active_learning_accurate_estim...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01538762, version 1

Citation

Carlos Riquelme, Mohammad Ghavamzadeh, Alessandro Lazaric. Active Learning for Accurate Estimation of Linear Models. ICML 2017 - 34th International Conference on Machine Learning, Aug 2017, Sydney, Australia. pp.36. 〈hal-01538762〉

Partager

Métriques

Consultations de la notice

235

Téléchargements de fichiers

39