Research map / Bandits and online learning / Multi-armed bandits
Fixed-confidence versus fixed-budget identification
Develop optimal elimination and top-two algorithms for confidence and budget settings.
35 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in Multi-armed bandits, keyword cluster “identification · best arm · pure exploration”
State History Tried 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.
5 papers in 2023–24 and 17 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.7% to 13.6%.
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
- 2019 · MaxGap Bandit: Adaptive Algorithms for Approximate Ranking (NeurIPS 2019 · 1 citation)
- 2020 · An Optimal Elimination Algorithm for Learning a Best Arm (NeurIPS 2020 · 4 citations)
- 2021 · Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification (NeurIPS 2021 · 1 citation)
- 2022 · On the Finite-Time Performance of the Knowledge Gradient Algorithm (ICML 2022 · 3 citations)
- 2023 · Improving the Knowledge Gradient Algorithm (NeurIPS 2023 · 1 citation)
- 2024 · Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · 1 citation)
- 2025 · Quantum Best Arm Identification with Quantum Oracles (AAAI 2025 · 2 citations)
- 2026 · Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors (ICML 2026 · 0 citations)
Earliest papers here
- MaxGap Bandit: Adaptive Algorithms for Approximate Ranking (NeurIPS 2019 · 1 citation)
- An Optimal Elimination Algorithm for Learning a Best Arm (NeurIPS 2020 · 4 citations)
- From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce Model (ICML 2020 · 1 citation)
What has been tried
20 papers here report 105 measured changes (a component added, removed or swapped, compared with a baseline): helped 64%, no clear effect 5%, hurt 28%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add arm elimination | 10-arm Gaussian prior, δ=0.01 · Avg stopping time | 1.29\times 10^6 -> 2.69\times 10^5 | Helped | Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 22 papers; from OpenAlex and the papers' affiliations).
- Inria · 2 papers
Use it
Download BibTeX of 32 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
- Best-arm identification in linear bandits (57 papers)
- Pure exploration algorithms (57 papers)
Elsewhere in the topic
- Non-stationary and structured-reward bandits (140 papers)
- Optimal stochastic bandit algorithms (124 papers)
- Multi-agent bandits (42 papers)
- Bandit formulations for ML problems (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).