Journal article · 2012 · Open access

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

Niranjan Srinivas, Andreas Krause, Sham M. Kakade, Matthias Seeger

IEEE Transactions on Information Theory, 58(5), 3250–3265 · Published 25 January 2012 · DOI 10.1109/tit.2011.2182033

Open PDFView at the publisherCite this paper

In brief

“Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting” is a 2012 journal article by Niranjan Srinivas and 3 co-authors, published in IEEE Transactions on Information Theory. OpenAlex counts 3,128 citations as of 19 November 2026, which puts it in the top 1% of works published in 2012 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
3,128
Most cited in
2021 (383)
Field-weighted impact
77.47
References
43
Authors
4

Abstract

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low norm in a reproducing kernel Hilbert space. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze an intuitive Gaussian process upper confidence bound (GP-UCB) algorithm, and bound its cumulative regret in terms of maximal in- formation gain, establishing a novel connection between GP optimization and experimental design. Moreover, by bounding the latter in terms of operator spectra, we obtain explicit sublinear regret bounds for many commonly used covariance functions. In some important cases, our bounds have surprisingly weak dependence on the dimensionality. In our experiments on real sensor data, GP-UCB compares favorably with other heuristical GP optimization approaches.

Cite this paper

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

APA 7

Srinivas, N., Krause, A., Kakade, S. M., & Seeger, M. (2012). Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting. IEEE Transactions on Information Theory, 58(5), 3250–3265. https://doi.org/10.1109/tit.2011.2182033

MLA 9

Srinivas, Niranjan, et al. “Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting.” IEEE Transactions on Information Theory, vol. 58, no. 5, 2012, pp. 3250–3265. https://doi.org/10.1109/tit.2011.2182033.

Chicago

Srinivas, Niranjan, Andreas Krause, Sham M. Kakade, and Matthias Seeger. 2012. “Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting.” IEEE Transactions on Information Theory 58 (5): 3250–3265. https://doi.org/10.1109/tit.2011.2182033.

Harvard

Srinivas, N. et al. (2012) ‘Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting’, IEEE Transactions on Information Theory, 58(5), pp. 3250–3265. doi:10.1109/tit.2011.2182033.

IEEE

N. Srinivas, A. Krause, S. M. Kakade, and M. Seeger, “Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting,” IEEE Transactions on Information Theory, vol. 58, no. 5, pp. 3250–3265, 2012, doi: 10.1109/tit.2011.2182033.

BibTeX

@article{srinivas2012information,
  title     = {{Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting}},
  author    = {Srinivas, Niranjan and Krause, Andreas and Kakade, Sham M. and Seeger, Matthias},
  journal   = {IEEE Transactions on Information Theory},
  year      = {2012},
  volume    = {58},
  number    = {5},
  pages     = {3250--3265},
  doi       = {10.1109/tit.2011.2182033},
  url       = {https://doi.org/10.1109/tit.2011.2182033}
}

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

Citations by year

YearCitationsShare of the best year
2017121121
2018149149
2019243243
2020375375
2021383383
2022275275
2023288288
2024320320
2025326326
2026337337

Its field-weighted citation impact is 77.47: it has been cited 77.47 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • Gaussian process optimization
  • multi-armed bandits
  • regret bounds
  • upper confidence bound
  • information gain
  • reproducing kernel Hilbert space
  • experimental design
  • operator spectrum

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?

Srinivas, N., Krause, A., Kakade, S. M., & Seeger, M. (2012). Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting. IEEE Transactions on Information Theory, 58(5), 3250–3265. https://doi.org/10.1109/tit.2011.2182033

How many times has this paper been cited?

3,128 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?

Niranjan Srinivas, Andreas Krause, Sham M. Kakade, Matthias Seeger.

What is the DOI of this paper?

10.1109/tit.2011.2182033, permanently at https://doi.org/10.1109/tit.2011.2182033. 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.