Preprint · 2022 · Open access

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization

Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

arXiv (Cornell University) · Published 15 March 2022 · DOI 10.48550/arxiv.2203.07875

Open PDFView at the publisherCite this paper

In brief

“Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization” is a 2022 preprint by Hung Tran-The and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 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
3
Most cited in
2025 (2)
References
23
Authors
4

Abstract

The expected improvement (EI) algorithm is one of the most popular strategies for optimization under uncertainty due to its simplicity and efficiency. Despite its popularity, the theoretical aspects of this algorithm have not been properly analyzed. In particular, whether in the noisy setting, the EI strategy with a standard incumbent converges is still an open question of the Gaussian process bandit optimization problem. We aim to answer this question by proposing a variant of EI with a standard incumbent defined via the GP predictive mean. We prove that our algorithm converges, and achieves a cumulative regret bound of $\mathcal O(γ_T\sqrt{T})$, where $γ_T$ is the maximum information gain between $T$ observations and the Gaussian process model. Based on this variant of EI, we further propose an algorithm called Improved GP-EI that converges faster than previous counterparts. In particular, our proposed variants of EI do not require the knowledge of the RKHS norm and the noise's sub-Gaussianity parameter as in previous works. Empirical validation in our paper demonstrates the effectiveness of our algorithms compared to several baselines.

Cite this paper

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

APA 7

Tran-The, H., Gupta, S., Rana, S., & Venkatesh, S. (2022). Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2203.07875

MLA 9

Tran-The, Hung, et al. “Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2203.07875.

Chicago

Tran-The, Hung, Sunil Gupta, Santu Rana, and Svetha Venkatesh. 2022. “Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2203.07875.

Harvard

Tran-The, H. et al. (2022) ‘Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization’, arXiv (Cornell University). doi:10.48550/arxiv.2203.07875.

IEEE

H. Tran-The, S. Gupta, S. Rana, and S. Venkatesh, “Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2203.07875.

BibTeX

@misc{tranthe2022regret,
  title     = {{Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization}},
  author    = {Tran-The, Hung and Gupta, Sunil and Rana, Santu and Venkatesh, Svetha},
  howpublished = {arXiv (Cornell University)},
  year      = {2022},
  doi       = {10.48550/arxiv.2203.07875},
  url       = {https://doi.org/10.48550/arxiv.2203.07875}
}

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

  • expected improvement
  • regret bounds
  • convergence analysis
  • information gain
  • optimization under uncertainty

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?

Tran-The, H., Gupta, S., Rana, S., & Venkatesh, S. (2022). Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2203.07875

How many times has this paper been cited?

3 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?

Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh.

What is the DOI of this paper?

10.48550/arxiv.2203.07875, permanently at https://doi.org/10.48550/arxiv.2203.07875. 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.