Batched Neural Bandits
ACM / IMS Journal of Data Science · 2024
DOI: 10.1145/3592474 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM / IMS Journal of Data Science, 2024. Verfasst von Quanquan Gu und 4 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation CAREER, NSF, ONR.
Abstract (Originalsprache)
In many sequential decision-making problems, the individuals are split into several batches and the decision-maker is only allowed to change her policy at the end of batches. These batch problems have a large number of applications, ranging from clinical trials to crowdsourcing. Motivated by this, we study the stochastic contextual bandit problem for general reward distributions under the batched setting. We propose the BatchNeuralUCB algorithm which combines neural networks with optimism to address the exploration-exploitation tradeoff while keeping the total number of batches limited. We study BatchNeuralUCB under both fixed and adaptive batch size settings and prove that it achieves the same regret as the fully sequential version while reducing the number of policy updates considerably. We confirm our theoretical results via simulations on both synthetic and real-world datasets.
Förderung
- National Science Foundation CAREER
- NSF
- ONR
- AI Institute for Learning-Enabled Optimization at Scale
Zitieren
APA
Gu, Q., Karbasi, A., Khosravi, K., Mirrokni, V., & Zhou, D. (2024). Batched Neural Bandits. ACM / IMS Journal of Data Science. https://doi.org/10.1145/3592474
Vancouver
Gu Q, Karbasi A, Khosravi K, Mirrokni V, Zhou D. Batched Neural Bandits. ACM / IMS Journal of Data Science. 2024. doi:10.1145/3592474
BibTeX
@article{Gu2024,
author = {Gu, Quanquan and Karbasi, Amin and Khosravi, Khashayar and Mirrokni, Vahab and Zhou, Dongruo},
title = {Batched Neural Bandits},
journal = {ACM / IMS Journal of Data Science},
year = {2024},
doi = {10.1145/3592474}
}
EUVIMED