Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Gaussian process bandit regret
Tighten regret bounds for GP-UCB and Thompson sampling in Gaussian process optimization.
26 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Contextual bandits and Thompson sampling, keyword cluster “thompson sampling · bayesian · ts”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
6 papers in 2023–24 and 6 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.0% to 4.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations (NeurIPS 2016 · 63 citations)
- 2018 · Tight Regret Bounds for Bayesian Optimization in One Dimension (ICML 2018 · 7 citations)
- 2019 · Bayesian Optimization under Heavy-tailed Payoffs (NeurIPS 2019 · 8 citations)
- 2020 · Near-linear time Gaussian process optimization with adaptive batching and resparsification (ICML 2020 · 6 citations)
- 2021 · A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance (NeurIPS 2021 · 6 citations)
- 2022 · Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems (NeurIPS 2022 · 2 citations)
- 2023 · Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds (ICML 2023 · 2 citations)
- 2024 · Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (ICML 2024 · 1 citation)
- 2025 · Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · 0 citations)
- 2026 · On Regret Bounds of Thompson Sampling for Bayesian Optimization (ICML 2026 · 0 citations)
Earliest papers here
- Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations (NeurIPS 2016 · 63 citations)
- Tight Regret Bounds for Bayesian Optimization in One Dimension (ICML 2018 · 7 citations)
- Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior (NeurIPS 2018 · 4 citations)
What has been tried
22 papers here report 137 measured changes (a component added, removed or swapped, compared with a baseline): helped 67%, no clear effect 16%, hurt 15%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| lower the confidence parameter β_t through the tested parametrization | Luxembourg and Monaco evaluation routes · cumulative regret | Helped | Bayesian Analysis of Combinatorial Gaussian Process Bandits (ICLR 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Baselines
- GP-UCB · 3 of 5 papers
- Kernel-AMM-UCB · 2 of 5 papers
- REDS · 2 of 5 papers
- EXPLOIT+ · 2 of 5 papers
- GP-EI · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 12 papers; from OpenAlex and the papers' affiliations).
- LY Corporation · 5 papers
- MI-6 Ltd · 4 papers
- Nagoya Institute of Technology · 3 papers
- RIKEN · 2 papers
- Carnegie Mellon University · 2 papers
- Nagoya University · 2 papers
Use it
Download BibTeX of 25 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Thompson sampling analysis (84 papers)
Elsewhere in the topic
- Oracle-efficient contextual bandits (168 papers)
- Linear and generalized linear bandits (88 papers)
- Practical contextual bandit extensions (77 papers)
- Causal and structured bandits (61 papers)
- Ranking bandits (42 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).