Parameter Tuning by Simple Regret Algorithms and Multiple Simultaneous Hypothesis Testing

Amine Bourki 1 Matthieu Coulm 1 Philippe Rolet 2 Olivier Teytaud 2, 3 Paul Vayssière 1
3 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 : ``Simple regret'' algorithms are designed for noisy optimization in unstructured domains. In particular, this literature has shown that the uniform algorithm is indeed optimal asymptotically and suboptimal non-asymptotically. We investigate theoretically and experimentally the application of these algorithms, for automatic parameter tuning, in particular from the point of view of the number of samples required for ``uniform'' to be relevant and from the point of view of statistical guarantees. We see that for moderate numbers of arms, the possible improvement in terms of computational power required for statistical validation can't be more than linear as a function of the number of arms and provide a simple rule to check if the simple uniform algorithm (trivially parallel) is relevant. Our experiments are performed on the tuning of a Monte-Carlo Tree Search algorithm, a great recent tool for high-dimensional planning with particularly impressive results for difficult games and in particular the game of Go.
Type de document :
Communication dans un congrès
ICINCO2010, 2010, funchal madeira, Portugal. pp.10, 2010
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00467796
Contributeur : Olivier Teytaud <>
Soumis le : mardi 30 mars 2010 - 15:03:25
Dernière modification le : jeudi 11 janvier 2018 - 06:22:14
Document(s) archivé(s) le : jeudi 30 juin 2011 - 11:17:48

Fichier

tosubmit.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00467796, version 1

Citation

Amine Bourki, Matthieu Coulm, Philippe Rolet, Olivier Teytaud, Paul Vayssière. Parameter Tuning by Simple Regret Algorithms and Multiple Simultaneous Hypothesis Testing. ICINCO2010, 2010, funchal madeira, Portugal. pp.10, 2010. 〈inria-00467796〉

Partager

Métriques

Consultations de la notice

543

Téléchargements de fichiers

221