Using the H-divergence to Prune Probabilistic Automata - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Using the H-divergence to Prune Probabilistic Automata

Baptiste Jeudy
Jean-Philippe Peyrache
  • Fonction : Auteur
  • PersonId : 764766
  • IdRef : 20024910X
Marc Sebban

Résumé

A problem usually encountered in probabilistic automata learning is the difficulty to deal with large training samples and/or wide alphabets. This is partially due to the size of the resulting Probabilistic Prefix Tree (PPT) from which state merging-based learning algorithms are generally applied. In this paper, we propose a novel method to prune PPTs by making use of the H-divergence dH, recently introduced in the field of domain adaptation. dH is based on the classification error made by an hypothes is learned from unlabeled examples drawn according to two distributions to compare. Through a thorough comp arison with state-of-the-art divergence measures, we provide experimental evidences that demonstrate the efficiency of our method based on this simple and intuitive criterion.
Fichier non déposé

Dates et versions

hal-00618713 , version 1 (02-09-2011)

Identifiants

  • HAL Id : hal-00618713 , version 1

Citer

Marc Bernard, Baptiste Jeudy, Jean-Philippe Peyrache, Marc Sebban, Franck Thollard. Using the H-divergence to Prune Probabilistic Automata. ICTAI 2011, Nov 2011, Boca Raton, United States. ⟨hal-00618713⟩
190 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More