Tight Regret Bounds for Infinite-armed Linear Contextual Bandits
Machine Learning
2021-01-28 v3 Machine Learning
Abstract
Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks. While there is a lot of prior research, tight regret bounds of linear contextual bandit with infinite action sets remain open. In this paper, we address this open problem by considering the linear contextual bandit with (changing) infinite action sets. We prove a regret upper bound on the order of where is the domain dimension and is the time horizon. Our upper bound matches the previous lower bound of in [Li et al., 2019] up to iterated logarithmic terms.
Keywords
Cite
@article{arxiv.1905.01435,
title = {Tight Regret Bounds for Infinite-armed Linear Contextual Bandits},
author = {Yingkai Li and Yining Wang and Xi Chen and Yuan Zhou},
journal= {arXiv preprint arXiv:1905.01435},
year = {2021}
}
Comments
10 pages, accepted for presentation at AISTATS 2021