Nearest Neighbour with Bandit Feedback

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pasteris, Stephen, Hicks, Chris, Mavroudis, Vasilios
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910358022651904
author Pasteris, Stephen
Hicks, Chris
Mavroudis, Vasilios
author_facet Pasteris, Stephen
Hicks, Chris
Mavroudis, Vasilios
contents In this paper we adapt the nearest neighbour rule to the contextual bandit problem. Our algorithm handles the fully adversarial setting in which no assumptions at all are made about the data-generation process. When combined with a sufficiently fast data-structure for (perhaps approximate) adaptive nearest neighbour search, such as a navigating net, our algorithm is extremely efficient - having a per trial running time polylogarithmic in both the number of trials and actions, and taking only quasi-linear space. We give generic regret bounds for our algorithm and further analyse them when applied to the stochastic bandit problem in euclidean space. We note that our algorithm can also be applied to the online classification problem.
format Preprint
id arxiv_https___arxiv_org_abs_2306_13773
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Nearest Neighbour with Bandit Feedback
Pasteris, Stephen
Hicks, Chris
Mavroudis, Vasilios
Machine Learning
In this paper we adapt the nearest neighbour rule to the contextual bandit problem. Our algorithm handles the fully adversarial setting in which no assumptions at all are made about the data-generation process. When combined with a sufficiently fast data-structure for (perhaps approximate) adaptive nearest neighbour search, such as a navigating net, our algorithm is extremely efficient - having a per trial running time polylogarithmic in both the number of trials and actions, and taking only quasi-linear space. We give generic regret bounds for our algorithm and further analyse them when applied to the stochastic bandit problem in euclidean space. We note that our algorithm can also be applied to the online classification problem.
title Nearest Neighbour with Bandit Feedback
topic Machine Learning
url https://arxiv.org/abs/2306.13773