Preprint · 2024 · Open access

On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise

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

arXiv (Cornell University) · Published 25 December 2024 · DOI 10.48550/arxiv.2412.18789

Open PDFView at the publisherCite this paper

In brief

“On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise” is a 2024 preprint by Jingyi Wang and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2025 (1)
References
16
Authors
4

Abstract

Bayesian optimization (BO) with Gaussian process (GP) surrogate models is a powerful black-box optimization method. Acquisition functions are a critical part of a BO algorithm as they determine how the new samples are selected. Some of the most widely used acquisition functions include upper confidence bound (UCB) and Thompson sampling (TS). The convergence analysis of BO algorithms has focused on the cumulative regret under both the Bayesian and frequentist settings for the objective. In this paper, we establish new pointwise bounds on the prediction error of GP under the frequentist setting with Gaussian noise. Consequently, we prove improved convergence rates of cumulative regret bound for both GP-UCB and GP-TS. Of note, the new prediction error bound under Gaussian noise can be applied to general BO algorithms and convergence analysis, e.g., the asymptotic convergence of expected improvement (EI) with noise.

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., Petra, C. G., & Chiang, N.-Y. (2024). On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2412.18789

MLA 9

Wang, Jingyi, et al. “On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2412.18789.

Chicago

Wang, Jingyi, Wang, Haowei, Cosmin G. Petra, and Nai-Yuan Chiang. 2024. “On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2412.18789.

Harvard

Wang, J. et al. (2024) ‘On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise’, arXiv (Cornell University). doi:10.48550/arxiv.2412.18789.

IEEE

J. Wang, W. Haowei, C. G. Petra, and N.-Y. Chiang, “On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2412.18789.

BibTeX

@misc{wang2024improved,
  title     = {{On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise}},
  author    = {Wang, Jingyi and Haowei, Wang, and Petra, Cosmin G. and Chiang, Nai-Yuan},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2412.18789},
  url       = {https://doi.org/10.48550/arxiv.2412.18789}
}

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
  • Kriging surrogate model
  • acquisition functions
  • Gaussian noise
  • upper confidence bound
  • Thompson sampling
  • expected improvement
  • black-box optimization

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., Petra, C. G., & Chiang, N.-Y. (2024). On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2412.18789

How many times has this paper been cited?

2 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, Cosmin G. Petra, Nai-Yuan Chiang.

What is the DOI of this paper?

10.48550/arxiv.2412.18789, permanently at https://doi.org/10.48550/arxiv.2412.18789. 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.