Year: 2025
Type: preprint
Abstract: In a fixed-confidence pure exploration problem in stochastic multi-armed bandits, an algorithm iteratively samples arms and should stop as early as possible and return the correct answer to a query about the arms distributions. We are interested in batched methods, which change their sampling behaviour only a few times, between batches of observations. We give an instance-dependent lower bound on the number of batches used by any sample efficient algorithm for any pure exploration task. We then give a general batched algorithm and prove upper bounds on its expected sample complexity and batch complexity. We illustrate both lower and upper bounds on best-arm identification and thresholding bandits.
Source: arXiv (Cornell University)
Authors: Tuynman, Adrienne, Degenne, Rémy
Institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, Université de Lille, Centre de Recherche en Informatique, Signal et Automatique de Lille, SCOOL: Prise de décision séquentielle dans l'incertain, Centrale Lille Institut
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
OpenAlex ID: W4407170376