Rising Rested Bandits: Lower Bounds and Efficient Algorithms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fiandri, Marco, Metelli, Alberto Maria, Trov`o, Francesco
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913586989760512
author Fiandri, Marco
Metelli, Alberto Maria
Trov`o, Francesco
author_facet Fiandri, Marco
Metelli, Alberto Maria
Trov`o, Francesco
contents This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e. those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. $arm$). We study a particular case of the rested bandits in which the arms' expected reward is monotonically non-decreasing and concave. We study the inherent sample complexity of the regret minimization problem by deriving suitable regret lower bounds. Then, we design an algorithm for the rested case $\textit{R-ed-UCB}$, providing a regret bound depending on the properties of the instance and, under certain circumstances, of $\widetilde{\mathcal{O}}(T^{\frac{2}{3}})$. We empirically compare our algorithms with state-of-the-art methods for non-stationary MABs over several synthetically generated tasks and an online model selection problem for a real-world dataset
format Preprint
id arxiv_https___arxiv_org_abs_2411_14446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rising Rested Bandits: Lower Bounds and Efficient Algorithms
Fiandri, Marco
Metelli, Alberto Maria
Trov`o, Francesco
Machine Learning
This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e. those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. $arm$). We study a particular case of the rested bandits in which the arms' expected reward is monotonically non-decreasing and concave. We study the inherent sample complexity of the regret minimization problem by deriving suitable regret lower bounds. Then, we design an algorithm for the rested case $\textit{R-ed-UCB}$, providing a regret bound depending on the properties of the instance and, under certain circumstances, of $\widetilde{\mathcal{O}}(T^{\frac{2}{3}})$. We empirically compare our algorithms with state-of-the-art methods for non-stationary MABs over several synthetically generated tasks and an online model selection problem for a real-world dataset
title Rising Rested Bandits: Lower Bounds and Efficient Algorithms
topic Machine Learning
url https://arxiv.org/abs/2411.14446