Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles

Résumé

We study contextual linear bandit problems under feature uncertainty; they are noisy with missing entries. To address the challenges of the noise, we analyze Bayesian oracles given observed noisy features. Our Bayesian analysis finds that the optimal hypothesis can be far from the underlying realizability function, depending on the noise characteristics, which are highly non-intuitive and do not occur for classical noiseless setups. This implies that classical approaches cannot guarantee a non-trivial regret bound. Therefore, we propose an algorithm that aims at the Bayesian oracle from observed information under this model, achieving $\tilde{O}(d\sqrt{T})$ regret bound when there is a large number of arms. We demonstrate the proposed algorithm using synthetic and real-world datasets.

Dates et versions

hal-04301930 , version 1 (23-11-2023)

Identifiants

Citer

Jung-Hun Kim, Se-Young Yun, Minchan Jeong, Jun Hyun Nam, Jinwoo Shin, et al.. Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles. AISTATS, 2023, Valencia, Spain. ⟨hal-04301930⟩
24 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More