Preprint · 2024 · Open access
Efficient and Adaptive Posterior Sampling Algorithms for Bandits
arXiv (Cornell University) · Published 2 May 2024 · DOI 10.48550/arxiv.2405.01010
In brief
“Efficient and Adaptive Posterior Sampling Algorithms for Bandits” is a 2024 preprint by Bingshan Hu and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 12
- Authors
- 5
Abstract
We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$, we derive a more practical bound that tightens the coefficient of the leading term %from $288 e^{64}$ to $1270$. Additionally, motivated by large-scale real-world applications that require scalability, adaptive computational resource allocation, and a balance in utility and computation, we propose two parameterized Thompson Sampling-based algorithms: Thompson Sampling with Model Aggregation (TS-MA-$α$) and Thompson Sampling with Timestamp Duelling (TS-TD-$α$), where $α\in [0,1]$ controls the trade-off between utility and computation. Both algorithms achieve $O \left(K\ln^{α+1}(T)/Δ\right)$ regret bound, where $K$ is the number of arms, $T$ is the finite learning horizon, and $Δ$ denotes the single round performance loss when pulling a sub-optimal arm.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hu, B., Zhiming, H., Zhang, T. H., Lécuyer, M., & Hegde, N. (2024). Efficient and Adaptive Posterior Sampling Algorithms for Bandits. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.01010
MLA 9
Hu, Bingshan, et al. “Efficient and Adaptive Posterior Sampling Algorithms for Bandits.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2405.01010.
Chicago
Hu, Bingshan, Huang, Zhiming, Tianyue H. Zhang, Mathias Lécuyer, and Nidhi Hegde. 2024. “Efficient and Adaptive Posterior Sampling Algorithms for Bandits.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.01010.
Harvard
Hu, B. et al. (2024) ‘Efficient and Adaptive Posterior Sampling Algorithms for Bandits’, arXiv (Cornell University). doi:10.48550/arxiv.2405.01010.
IEEE
B. Hu, H. Zhiming, T. H. Zhang, M. Lécuyer, and N. Hegde, “Efficient and Adaptive Posterior Sampling Algorithms for Bandits,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2405.01010.
BibTeX
@misc{hu2024efficient,
title = {{Efficient and Adaptive Posterior Sampling Algorithms for Bandits}},
author = {Hu, Bingshan and Zhiming, Huang, and Zhang, Tianyue H. and Lécuyer, Mathias and Hegde, Nidhi},
howpublished = {arXiv (Cornell University)},
year = {2024},
doi = {10.48550/arxiv.2405.01010},
url = {https://doi.org/10.48550/arxiv.2405.01010}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- Thompson sampling
- stochastic bandits
- regret bounds
- Gaussian prior
- model aggregation
- scalability
Work with this paper
Most-cited papers in Decision Sciences
- The PRISMA 2020 statement: an updated guideline for reporting systematic reviewsMatthew James Page, Joanne E. McKenzie, Patrick M. Bossuyt and 23 more · BMJ · 2021 · 144,919 citations
- Evaluating Structural Equation Models with Unobservable Variables and Measurement ErrorClaes Fornell, David F. Larcker · Journal of Marketing Research · 1981 · 118,336 citations
- Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternativesLi‐tze Hu, Peter M. Bentler · Structural Equation Modeling A Multidisciplinary Journal · 1999 · 117,461 citations
- Common method biases in behavioral research: A critical review of the literature and recommended remedies.Philip M. Podsakoff, SCOTT B. MACKENZIE, Jeong Yeon Lee and 1 more · Journal of Applied Psychology · 2003 · 89,248 citations
- Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statementDavid Moher, Alessandro Liberati, Jennifer Tetzlaff and 2 more · BMJ · 2009 · 85,524 citations
Questions about this paper
How do I cite this paper in APA style?
Hu, B., Zhiming, H., Zhang, T. H., Lécuyer, M., & Hegde, N. (2024). Efficient and Adaptive Posterior Sampling Algorithms for Bandits. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.01010
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Bingshan Hu, Huang, Zhiming, Tianyue H. Zhang, Mathias Lécuyer, Nidhi Hegde.
What is the DOI of this paper?
10.48550/arxiv.2405.01010, permanently at https://doi.org/10.48550/arxiv.2405.01010. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.