Preprint · 2025 · Open access

On the convergence rate of noisy Bayesian Optimization with Expected Improvement

Jingyi Wang, Wang, Haowei, Nai-Yuan Chiang, Cosmin G. Petra

arXiv (Cornell University) · Published 16 January 2025 · DOI 10.48550/arxiv.2501.09262

Open PDFView at the publisherCite this paper

In brief

“On the convergence rate of noisy Bayesian Optimization with Expected Improvement” is a 2025 preprint by Jingyi Wang and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 5 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
5
Most cited in
2026 (3)
References
22
Authors
4

Abstract

Expected improvement (EI) is one of the most widely used acquisition functions in Bayesian optimization (BO). Despite its proven success in applications for decades, important open questions remain on the theoretical convergence behaviors and rates for EI. In this paper, we contribute to the convergence theory of EI in three novel and critical areas. First, we consider objective functions that fit under the Gaussian process (GP) prior assumption, whereas existing works mostly focus on functions in the reproducing kernel Hilbert space (RKHS). Second, we establish for the first time the asymptotic error bound and its corresponding rate for GP-EI with noisy observations under the GP prior assumption. Third, by investigating the exploration and exploitation properties of the non-convex EI function, we establish improved error bounds of GP-EI for both the noise-free and noisy cases.

Cite this paper

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

APA 7

Wang, J., Haowei, W., Chiang, N.-Y., & Petra, C. G. (2025). On the convergence rate of noisy Bayesian Optimization with Expected Improvement. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.09262

MLA 9

Wang, Jingyi, et al. “On the convergence rate of noisy Bayesian Optimization with Expected Improvement.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2501.09262.

Chicago

Wang, Jingyi, Wang, Haowei, Nai-Yuan Chiang, and Cosmin G. Petra. 2025. “On the convergence rate of noisy Bayesian Optimization with Expected Improvement.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.09262.

Harvard

Wang, J. et al. (2025) ‘On the convergence rate of noisy Bayesian Optimization with Expected Improvement’, arXiv (Cornell University). doi:10.48550/arxiv.2501.09262.

IEEE

J. Wang, W. Haowei, N.-Y. Chiang, and C. G. Petra, “On the convergence rate of noisy Bayesian Optimization with Expected Improvement,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2501.09262.

BibTeX

@misc{wang2025convergence,
  title     = {{On the convergence rate of noisy Bayesian Optimization with Expected Improvement}},
  author    = {Wang, Jingyi and Haowei, Wang, and Chiang, Nai-Yuan and Petra, Cosmin G.},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2501.09262},
  url       = {https://doi.org/10.48550/arxiv.2501.09262}
}

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

  • Bayesian optimization
  • expected improvement
  • noisy measurements
  • convergence rate
  • Gaussian process priors
  • asymptotic error bounds
  • acquisition functions
  • exploration and exploitation

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, J., Haowei, W., Chiang, N.-Y., & Petra, C. G. (2025). On the convergence rate of noisy Bayesian Optimization with Expected Improvement. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.09262

How many times has this paper been cited?

5 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?

Jingyi Wang, Wang, Haowei, Nai-Yuan Chiang, Cosmin G. Petra.

What is the DOI of this paper?

10.48550/arxiv.2501.09262, permanently at https://doi.org/10.48550/arxiv.2501.09262. 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.