Preprint · 2016 · Open access

Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

Li, Lisha, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar

arXiv (Cornell University), 18(1), 6765–6816 · Published 21 March 2016 · DOI 10.48550/arxiv.1603.06560

Open PDFView at the publisherCite this paper

In brief

“Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization” is a 2016 preprint by Li, Lisha and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 2,630 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2,630
Most cited in
2023 (455)
References
52
Authors
5

Abstract

Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation and early-stopping. We formulate hyperparameter optimization as a pure-exploration non-stochastic infinite-armed bandit problem where a predefined resource like iterations, data samples, or features is allocated to randomly sampled configurations. We introduce a novel algorithm, Hyperband, for this framework and analyze its theoretical properties, providing several desirable guarantees. Furthermore, we compare Hyperband with popular Bayesian optimization methods on a suite of hyperparameter optimization problems. We observe that Hyperband can provide over an order-of-magnitude speedup over our competitor set on a variety of deep-learning and kernel-based learning problems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Lisha, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2016). Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. arXiv (Cornell University), 18(1), 6765–6816. https://doi.org/10.48550/arxiv.1603.06560

MLA 9

Lisha, Li,, et al. “Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization.” arXiv (Cornell University), vol. 18, no. 1, 2016, pp. 6765–6816. https://doi.org/10.48550/arxiv.1603.06560.

Chicago

Lisha, Li,, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, and Ameet Talwalkar. 2016. “Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization.” arXiv (Cornell University) 18 (1): 6765–6816. https://doi.org/10.48550/arxiv.1603.06560.

Harvard

Lisha, L. et al. (2016) ‘Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization’, arXiv (Cornell University), 18(1), pp. 6765–6816. doi:10.48550/arxiv.1603.06560.

IEEE

L. Lisha, K. Jamieson, G. DeSalvo, A. Rostamizadeh, and A. Talwalkar, “Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization,” arXiv (Cornell University), vol. 18, no. 1, pp. 6765–6816, 2016, doi: 10.48550/arxiv.1603.06560.

BibTeX

@misc{lisha2016hyperband,
  title     = {{Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization}},
  author    = {Lisha, Li, and Jamieson, Kevin and DeSalvo, Giulia and Rostamizadeh, Afshin and Talwalkar, Ameet},
  howpublished = {arXiv (Cornell University)},
  year      = {2016},
  volume    = {18},
  number    = {1},
  pages     = {6765--6816},
  doi       = {10.48550/arxiv.1603.06560},
  url       = {https://doi.org/10.48550/arxiv.1603.06560}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20173434
20185252
2019155155
2020300300
2021358358
2022356356
2023455455
2024393393
2025336336
2026190190

Topic and keywords

Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research

  • hyperparameter optimization
  • pure exploration
  • random search
  • adaptive resource allocation
  • early stopping
  • Bayesian optimization comparison
  • kernel learning

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Lisha, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2016). Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. arXiv (Cornell University), 18(1), 6765–6816. https://doi.org/10.48550/arxiv.1603.06560

How many times has this paper been cited?

2,630 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?

Li, Lisha, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar.

What is the DOI of this paper?

10.48550/arxiv.1603.06560, permanently at https://doi.org/10.48550/arxiv.1603.06560. 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.