On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2023

On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm

Résumé

When fitting the learning data of an individual to algorithm-like learning models, the observations are so dependent and non-stationary that one may wonder what the classical Maximum Likelihood Estimator (MLE) could do, even if it is the usual tool applied to experimental cognition. Our objective in this work is to show that the estimation of the learning rate cannot be efficient if the learning rate is constant in the classical Exp3 (Exponential weights for Exploration and Exploitation) algorithm. Secondly, we show that if the learning rate decreases polynomially with the sample size, then the prediction error and in some cases the estimation error of the MLE satisfy bounds in probability that decrease at a polynomial rate.
Fichier principal
Vignette du fichier
Exp3___ICML___Arxiv (3).pdf (504.4 Ko) Télécharger le fichier
Exp3R.zip (7.84 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04083986 , version 1 (10-05-2023)
hal-04083986 , version 2 (11-10-2023)

Licence

Paternité

Identifiants

Citer

Julien Aubert, Luc Lehéricy, Patricia Reynaud-Bouret. On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm. 2023. ⟨hal-04083986v1⟩
99 Consultations
21 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More