Feature Selection for SUNNY: a Study on the Algorithm Selection Library

Roberto Amadini 1, 2 Fabio Biselli 1 Maurizio Gabbrielli 2, 1 Tong Liu 1 Jacopo Mauro 2, 1
2 FOCUS - Foundations of Component-based Ubiquitous Systems
CRISAM - Inria Sophia Antipolis - Méditerranée , DISI - Dipartimento di Informatica - Scienza e Ingegneria [Bologna]
Abstract : Given a collection of algorithms, the Algorithm Selection (AS) problem consists in identifying which of them is the best one for solving a given problem. The selection depends on a set of numerical features that characterize the problem to solve. In this paper we show the impact of feature selection techniques on the performance of the SUNNY algorithm selector, taking as reference the benchmarks of the AS library (ASlib). Results indicate that a handful of features is enough to reach similar, if not better, performance of the original SUNNY approach that uses all the available features. We also present sunny-as: a tool for using SUNNY on a generic ASlib scenario.
Type de document :
Communication dans un congrès
ICTAI, Nov 2015, Vietri sul Mare, Italy
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

Contributeur : Amadini Roberto <>
Soumis le : mercredi 11 novembre 2015 - 16:59:53
Dernière modification le : mercredi 10 octobre 2018 - 10:09:14
Document(s) archivé(s) le : vendredi 28 avril 2017 - 05:12:26


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


  • HAL Id : hal-01227600, version 1



Roberto Amadini, Fabio Biselli, Maurizio Gabbrielli, Tong Liu, Jacopo Mauro. Feature Selection for SUNNY: a Study on the Algorithm Selection Library. ICTAI, Nov 2015, Vietri sul Mare, Italy. 〈hal-01227600〉



Consultations de la notice


Téléchargements de fichiers