Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thuot, Victor, Carpentier, Alexandra, Giraud, Christophe, Verzelen, Nicolas
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.11485
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917696139952128
author Thuot, Victor
Carpentier, Alexandra
Giraud, Christophe
Verzelen, Nicolas
author_facet Thuot, Victor
Carpentier, Alexandra
Giraud, Christophe
Verzelen, Nicolas
contents We investigate the Active Clustering Problem (ACP). A learner interacts with an $N$-armed stochastic bandit with $d$-dimensional subGaussian feedback. There exists a hidden partition of the arms into $K$ groups, such that arms within the same group, share the same mean vector. The learner's task is to uncover this hidden partition with the smallest budget - i.e., the least number of observation - and with a probability of error smaller than a prescribed constant $δ$. In this paper, (i) we derive a non-asymptotic lower bound for the budget, and (ii) we introduce the computationally efficient ACB algorithm, whose budget matches the lower bound in most regimes. We improve on the performance of a uniform sampling strategy. Importantly, contrary to the batch setting, we establish that there is no computation-information gap in the active setting.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11485
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Active clustering with bandit feedback
Thuot, Victor
Carpentier, Alexandra
Giraud, Christophe
Verzelen, Nicolas
Machine Learning
We investigate the Active Clustering Problem (ACP). A learner interacts with an $N$-armed stochastic bandit with $d$-dimensional subGaussian feedback. There exists a hidden partition of the arms into $K$ groups, such that arms within the same group, share the same mean vector. The learner's task is to uncover this hidden partition with the smallest budget - i.e., the least number of observation - and with a probability of error smaller than a prescribed constant $δ$. In this paper, (i) we derive a non-asymptotic lower bound for the budget, and (ii) we introduce the computationally efficient ACB algorithm, whose budget matches the lower bound in most regimes. We improve on the performance of a uniform sampling strategy. Importantly, contrary to the batch setting, we establish that there is no computation-information gap in the active setting.
title Active clustering with bandit feedback
topic Machine Learning
url https://arxiv.org/abs/2406.11485