Preprint · 2021 · Open access

Pre-trained Gaussian Processes for Bayesian Optimization

Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani

arXiv (Cornell University) · Published 16 September 2021 · DOI 10.48550/arxiv.2109.08215

Open PDFView at the publisherCite this paper

In brief

“Pre-trained Gaussian Processes for Bayesian Optimization” is a 2021 preprint by Zi Wang and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 65 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
65
Most cited in
2025 (20)
References
79
Authors
8

Abstract

Bayesian optimization (BO) has become a popular strategy for global optimization of expensive real-world functions. Contrary to a common expectation that BO is suited to optimizing black-box functions, it actually requires domain knowledge about those functions to deploy BO successfully. Such domain knowledge often manifests in Gaussian process (GP) priors that specify initial beliefs on functions. However, even with expert knowledge, it is non-trivial to quantitatively define a prior. This is especially true for hyperparameter tuning problems on complex machine learning models, where landscapes of tuning objectives are often difficult to comprehend. We seek an alternative practice for setting these functional priors. In particular, we consider the scenario where we have data from similar functions that allow us to pre-train a tighter distribution a priori. We detail what pre-training entails for GPs using a KL divergence based loss function, and propose a new pre-training based BO framework named HyperBO. Theoretically, we show bounded posterior predictions and near-zero regrets for HyperBO without assuming the "ground truth" GP prior is known. To verify our approach in realistic setups, we collect a large multi-task hyperparameter tuning dataset by training tens of thousands of configurations of near-state-of-the-art deep learning models on popular image and text datasets, as well as a protein sequence dataset. Our results show that on average, HyperBO is able to locate good hyperparameters at least 3 times more efficiently than the best competing methods on both our new tuning dataset and existing multi-task BO benchmarks.

Cite this paper

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

APA 7

Wang, Z., Dahl, G. E., Swersky, K., Lee, C., Nado, Z., Gilmer, J., Snoek, J., & Ghahramani, Z. (2021). Pre-trained Gaussian Processes for Bayesian Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2109.08215

MLA 9

Wang, Zi, et al. “Pre-trained Gaussian Processes for Bayesian Optimization.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2109.08215.

Chicago

Wang, Zi, George E. Dahl, Kevin Swersky, Chansoo Lee, Zachary Nado, Justin Gilmer, Jasper Snoek, and Zoubin Ghahramani. 2021. “Pre-trained Gaussian Processes for Bayesian Optimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2109.08215.

Harvard

Wang, Z. et al. (2021) ‘Pre-trained Gaussian Processes for Bayesian Optimization’, arXiv (Cornell University). doi:10.48550/arxiv.2109.08215.

IEEE

Z. Wang et al., “Pre-trained Gaussian Processes for Bayesian Optimization,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2109.08215.

BibTeX

@misc{wang2021trained,
  title     = {{Pre-trained Gaussian Processes for Bayesian Optimization}},
  author    = {Wang, Zi and Dahl, George E. and Swersky, Kevin and Lee, Chansoo and Nado, Zachary and Gilmer, Justin and Snoek, Jasper and Ghahramani, Zoubin},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  doi       = {10.48550/arxiv.2109.08215},
  url       = {https://doi.org/10.48550/arxiv.2109.08215}
}

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

Citations by year

YearCitationsShare of the best year
202266
20231212
20241010
20252020
20261717

Topic and keywords

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

  • Bayesian optimization
  • Gaussian process priors
  • pre-training
  • hyperparameter optimization
  • KL divergence loss
  • expensive black-box functions
  • regret analysis

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?

Wang, Z., Dahl, G. E., Swersky, K., Lee, C., Nado, Z., Gilmer, J., Snoek, J., & Ghahramani, Z. (2021). Pre-trained Gaussian Processes for Bayesian Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2109.08215

How many times has this paper been cited?

65 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?

Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani.

What is the DOI of this paper?

10.48550/arxiv.2109.08215, permanently at https://doi.org/10.48550/arxiv.2109.08215. 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.