Preprint · 2019 · Open access

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret

Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Valko, Michal, Lorenzo Rosasco

arXiv (Cornell University) · Published 13 March 2019 · DOI 10.48550/arxiv.1903.05594

Open PDFView at the publisherCite this paper

In brief

“Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret” is a 2019 preprint by Daniele Calandriello and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 87 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
87
Most cited in
2020 (21)
References
36
Authors
5

Abstract

Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions $d$ and iterations $t$. Given a set of $A$ alternatives to choose from, the overall runtime $O(t^3A)$ is prohibitive. In this paper we introduce BKB (budgeted kernelized bandit), a new approximate GP algorithm for optimization under bandit feedback that achieves near-optimal regret (and hence near-optimal convergence rate) with near-constant per-iteration complexity and remarkably no assumption on the input space or covariance of the GP. We combine a kernelized linear bandit algorithm (GP-UCB) with randomized matrix sketching based on leverage score sampling, and we prove that randomly sampling inducing points based on their posterior variance gives an accurate low-rank approximation of the GP, preserving variance estimates and confidence intervals. As a consequence, BKB does not suffer from variance starvation, an important problem faced by many previous sparse GP approximations. Moreover, we show that our procedure selects at most $\tilde{O}(d_{eff})$ points, where $d_{eff}$ is the effective dimension of the explored space, which is typically much smaller than both $d$ and $t$. This greatly reduces the dimensionality of the problem, thus leading to a $O(TAd_{eff}^2)$ runtime and $O(A d_{eff})$ space complexity.

Cite this paper

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

APA 7

Calandriello, D., Carratino, L., Lazaric, A., Michal, V., & Rosasco, L. (2019). Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1903.05594

MLA 9

Calandriello, Daniele, et al. “Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret.” arXiv (Cornell University), 2019. https://doi.org/10.48550/arxiv.1903.05594.

Chicago

Calandriello, Daniele, Luigi Carratino, Alessandro Lazaric, Valko, Michal, and Lorenzo Rosasco. 2019. “Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1903.05594.

Harvard

Calandriello, D. et al. (2019) ‘Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret’, arXiv (Cornell University). doi:10.48550/arxiv.1903.05594.

IEEE

D. Calandriello, L. Carratino, A. Lazaric, V. Michal, and L. Rosasco, “Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret,” arXiv (Cornell University), 2019, doi: 10.48550/arxiv.1903.05594.

BibTeX

@misc{calandriello2019gaussian,
  title     = {{Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret}},
  author    = {Calandriello, Daniele and Carratino, Luigi and Lazaric, Alessandro and Michal, Valko, and Rosasco, Lorenzo},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  doi       = {10.48550/arxiv.1903.05594},
  url       = {https://doi.org/10.48550/arxiv.1903.05594}
}

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

Citations by year

YearCitationsShare of the best year
201811
201933
20202121
20211818
20221212
202399
202477
20251111
202655

Topic and keywords

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

  • Gaussian process optimization
  • black-box optimization
  • bandit feedback
  • leverage score sampling
  • inducing points
  • low-rank approximation
  • regret bounds
  • scalable 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?

Calandriello, D., Carratino, L., Lazaric, A., Michal, V., & Rosasco, L. (2019). Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1903.05594

How many times has this paper been cited?

87 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?

Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Valko, Michal, Lorenzo Rosasco.

What is the DOI of this paper?

10.48550/arxiv.1903.05594, permanently at https://doi.org/10.48550/arxiv.1903.05594. 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.