Preprint · 2021 · Open access

Variational Bayesian Optimistic Sampling

Brendan O’Donoghue, Tor Lattimore

arXiv (Cornell University), 34 · Published 29 October 2021 · DOI 10.48550/arxiv.2110.15688

Open PDFView at the publisherCite this paper

In brief

“Variational Bayesian Optimistic Sampling” is a 2021 preprint by Brendan O’Donoghue and Tor Lattimore, published in arXiv (Cornell University). OpenAlex counts 1 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
1
Most cited in
2025 (1)
References
40
Authors
2

Abstract

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling policy. We provide a new analysis showing that any algorithm producing policies in the optimistic set enjoys $\tilde O(\sqrt{AT})$ Bayesian regret for a problem with $A$ actions after $T$ rounds. We extend the regret analysis for optimistic policies to bilinear saddle-point problems which include zero-sum matrix games and constrained bandits as special cases. In this case we show that Thompson sampling can produce policies outside of the optimistic set and suffer linear regret in some instances. Finding a policy inside the optimistic set amounts to solving a convex optimization problem and we call the resulting algorithm `variational Bayesian optimistic sampling' (VBOS). The procedure works for any posteriors, \ie, it does not require the posterior to have any special properties, such as log-concavity, unimodality, or smoothness. The variational view of the problem has many useful properties, including the ability to tune the exploration-exploitation tradeoff, add regularization, incorporate constraints, and linearly parameterize the policy.

Cite this paper

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

APA 7

O’Donoghue, B., & Lattimore, T. (2021). Variational Bayesian Optimistic Sampling. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2110.15688

MLA 9

O’Donoghue, Brendan, and Tor Lattimore. “Variational Bayesian Optimistic Sampling.” arXiv (Cornell University), vol. 34, 2021. https://doi.org/10.48550/arxiv.2110.15688.

Chicago

O’Donoghue, Brendan and Tor Lattimore. 2021. “Variational Bayesian Optimistic Sampling.” arXiv (Cornell University) 34. https://doi.org/10.48550/arxiv.2110.15688.

Harvard

O’Donoghue, B. and Lattimore, T. (2021) ‘Variational Bayesian Optimistic Sampling’, arXiv (Cornell University), 34. doi:10.48550/arxiv.2110.15688.

IEEE

B. O’Donoghue and T. Lattimore, “Variational Bayesian Optimistic Sampling,” arXiv (Cornell University), vol. 34, 2021, doi: 10.48550/arxiv.2110.15688.

BibTeX

@misc{odonoghue2021variational,
  title     = {{Variational Bayesian Optimistic Sampling}},
  author    = {O’Donoghue, Brendan and Lattimore, Tor},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  volume    = {34},
  doi       = {10.48550/arxiv.2110.15688},
  url       = {https://doi.org/10.48550/arxiv.2110.15688}
}

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

  • exploration-exploitation balance
  • Bayesian regret
  • Thompson sampling
  • multi-armed bandits
  • zero-sum matrix games
  • variational inference
  • convex optimization
  • regret analysis

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?

O’Donoghue, B., & Lattimore, T. (2021). Variational Bayesian Optimistic Sampling. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2110.15688

How many times has this paper been cited?

1 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?

Brendan O’Donoghue, Tor Lattimore.

What is the DOI of this paper?

10.48550/arxiv.2110.15688, permanently at https://doi.org/10.48550/arxiv.2110.15688. 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.