Preprint · 2026 · Open access

Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration

Matthias Mändl, Hanne Kekkonen

arXiv (Cornell University) · Published 19 August 2026 · DOI 10.48550/arxiv.2608.18863

Open PDFView at the publisherCite this paper

In brief

“Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration” is a 2026 preprint by Matthias Mändl and Hanne Kekkonen, published in arXiv (Cornell University). OpenAlex counts 0 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
0
References
19
Authors
2

Abstract

We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model. Existing GP-UCB analyses in this setting typically require the exploration parameter to grow with the horizon to maintain uniform confidence bounds. Using per-round local confidence events, we show that GP-UCB can instead be run with a constant exploration parameter and obtain an expected-regret bound whose coefficient depends on the drift rate. We also derive a sharper time-varying maximum-information-gain bound. For the squared exponential kernel, it yields $\tildeγ_T/T=\widetilde{\mathcal O}(ε^{1/2})$ and expected average regret $\widetilde{\mathcal O}(ε^{1/4})$ in the persistent-drift regime. The same constant-exploration analysis also yields realized-regret guarantees. Simulations support the predicted logarithmic dependence of the bound-suggested exploration parameter on $1/ε$.

Cite this paper

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

APA 7

Mändl, M., & Kekkonen, H. (2026). Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18863

MLA 9

Mändl, Matthias, and Hanne Kekkonen. “Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2608.18863.

Chicago

Mändl, Matthias and Hanne Kekkonen. 2026. “Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18863.

Harvard

Mändl, M. and Kekkonen, H. (2026) ‘Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration’, arXiv (Cornell University). doi:10.48550/arxiv.2608.18863.

IEEE

M. Mändl and H. Kekkonen, “Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2608.18863.

BibTeX

@misc{mandl2026sharper,
  title     = {{Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration}},
  author    = {Mändl, Matthias and Kekkonen, Hanne},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2608.18863},
  url       = {https://doi.org/10.48550/arxiv.2608.18863}
}

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

  • Gaussian process bandits
  • regret bounds
  • drift rate
  • Bayesian optimization
  • Gaussian kernel

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?

Mändl, M., & Kekkonen, H. (2026). Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.18863

How many times has this paper been cited?

0 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?

Matthias Mändl, Hanne Kekkonen.

What is the DOI of this paper?

10.48550/arxiv.2608.18863, permanently at https://doi.org/10.48550/arxiv.2608.18863. 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.