Saved in:
Bibliographic Details
Main Authors: Bilaj, Steven, Dhouib, Sofien, Maghsudi, Setareh
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.00688
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909155732750336
author Bilaj, Steven
Dhouib, Sofien
Maghsudi, Setareh
author_facet Bilaj, Steven
Dhouib, Sofien
Maghsudi, Setareh
contents We study the problem of meta-learning several contextual stochastic bandits tasks by leveraging their concentration around a low-dimensional affine subspace, which we learn via online principal component analysis to reduce the expected regret over the encountered bandits. We propose and theoretically analyze two strategies that solve the problem: One based on the principle of optimism in the face of uncertainty and the other via Thompson sampling. Our framework is generic and includes previously proposed approaches as special cases. Besides, the empirical results show that our methods significantly reduce the regret on several bandit tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00688
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Meta Learning in Bandits within Shared Affine Subspaces
Bilaj, Steven
Dhouib, Sofien
Maghsudi, Setareh
Machine Learning
We study the problem of meta-learning several contextual stochastic bandits tasks by leveraging their concentration around a low-dimensional affine subspace, which we learn via online principal component analysis to reduce the expected regret over the encountered bandits. We propose and theoretically analyze two strategies that solve the problem: One based on the principle of optimism in the face of uncertainty and the other via Thompson sampling. Our framework is generic and includes previously proposed approaches as special cases. Besides, the empirical results show that our methods significantly reduce the regret on several bandit tasks.
title Meta Learning in Bandits within Shared Affine Subspaces
topic Machine Learning
url https://arxiv.org/abs/2404.00688