Finite-sample analysis of Lasso-TD - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Finite-sample analysis of Lasso-TD

Mohammad Ghavamzadeh
  • Fonction : Auteur
  • PersonId : 868946
Alessandro Lazaric
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

In this paper, we analyze the performance of Lasso-TD, a modification of LSTD in which the projection operator is defined as a Lasso problem. We first show that Lasso-TD is guaranteed to have a unique fixed point and its algorithmic implementation coincides with the recently presented LARS-TD and LC-TD methods. We then derive two bounds on the prediction error of Lasso-TD in the Markov design setting, i.e., when the perfor- mance is evaluated on the same states used by the method. The first bound makes no as- sumption, but has a slow rate w.r.t. the number of samples. The second bound is under an assumption on the empirical Gram matrix, called the compatibility condition, but has an improved rate and directly relates the prediction error to the sparsity of the value function in the feature space at hand.
Fichier principal
Vignette du fichier
lasso-TD.pdf (223.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00830149 , version 1 (04-06-2013)

Identifiants

  • HAL Id : hal-00830149 , version 1

Citer

Mohammad Ghavamzadeh, Alessandro Lazaric, Rémi Munos, Matt Hoffman. Finite-sample analysis of Lasso-TD. International Conference on Machine Learning, 2011, United States. ⟨hal-00830149⟩
299 Consultations
253 Téléchargements

Partager

Gmail Facebook X LinkedIn More