Preprint · 2020 · Open access
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
arXiv (Cornell University) · Published 11 July 2020 · DOI 10.48550/arxiv.2007.05670
In brief
“An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization” is a 2020 preprint by Yimin Huang and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 8 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 8
- Most cited in
- 2020 (2)
- References
- 79
- Authors
- 5
Abstract
The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter optimization algorithm called BOSS. Empirical studies validate our theoretical arguments of SS and demonstrate the superior performance of BOSS on a number of applications, including Neural Architecture Search (NAS), Data Augmentation (DA), Object Detection (OD), and Reinforcement Learning (RL).
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Huang, Y., Li, Y., Ye, H., Li, Z., & Zhang, Z. (2020). An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2007.05670
MLA 9
Huang, Yimin, et al. “An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2007.05670.
Chicago
Huang, Yimin, Yujun Li, Hanrong Ye, Zhenguo Li, and Zhihua Zhang. 2020. “An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2007.05670.
Harvard
Huang, Y. et al. (2020) ‘An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization’, arXiv (Cornell University). doi:10.48550/arxiv.2007.05670.
IEEE
Y. Huang, Y. Li, H. Ye, Z. Li, and Z. Zhang, “An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2007.05670.
BibTeX
@misc{huang2020asymptotically,
title = {{An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization}},
author = {Huang, Yimin and Li, Yujun and Ye, Hanrong and Li, Zhenguo and Zhang, Zhihua},
howpublished = {arXiv (Cornell University)},
year = {2020},
doi = {10.48550/arxiv.2007.05670},
url = {https://doi.org/10.48550/arxiv.2007.05670}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2020 | 2 | |
| 2021 | 2 | |
| 2022 | 2 | |
| 2024 | 1 | |
| 2026 | 1 |
Topic and keywords
Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- multi-armed bandits
- hyperparameter optimization
- Bayesian optimization
- cumulative regret
- asymptotic optimality
- neural architecture search
- data augmentation
- object detection
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?
Huang, Y., Li, Y., Ye, H., Li, Z., & Zhang, Z. (2020). An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2007.05670
How many times has this paper been cited?
8 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?
Yimin Huang, Yujun Li, Hanrong Ye, Zhenguo Li, Zhihua Zhang.
What is the DOI of this paper?
10.48550/arxiv.2007.05670, permanently at https://doi.org/10.48550/arxiv.2007.05670. 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.