Research map / Learning theory and algorithms / Sample complexity
Sample complexity of ranking and selection
Bounds samples for item selection, ranking, boosting and auction learning.
80 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Sample complexity, keyword cluster “sample complexity · pac · optimal sample”
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.
16 papers in 2023–24 and 19 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.8% to 5.8%.
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 · The Power of Adaptivity in Identifying Statistical Alternatives (NeurIPS 2016 · 12 citations)
- 2017 · Vote Until Two of You Agree: Mechanisms with Small Distortion and Sample Complexity (AAAI 2017 · 45 citations)
- 2018 · Robust Hypothesis Testing Using Wasserstein Uncertainty Sets (NeurIPS 2018 · 34 citations)
- 2019 · Limiting Extrapolation in Linear Approximate Value Iteration (NeurIPS 2019 · 13 citations)
- 2020 · Statistical and Topological Properties of Sliced Probability Divergences (NeurIPS 2020 · 18 citations)
- 2021 · Empirical or Invariant Risk Minimization? A Sample Complexity Perspective (ICLR 2021 · 15 citations)
- 2022 · The Complexity of Subelection Isomorphism Problems (AAAI 2022 · 4 citations)
- 2023 · Provable Benefit of Mixup for Finding Optimal Decision Boundaries (ICML 2023 · 1 citation)
- 2024 · Faster Maximum Inner Product Search in High Dimensions (ICML 2024 · 1 citation)
- 2025 · Learnability of Parameter-Bounded Bayes Nets (AAAI 2025 · 0 citations)
- 2026 · Learning to Rank from Incomplete Rankings (ICML 2026 · 0 citations)
Earliest papers here
- The Power of Adaptivity in Identifying Statistical Alternatives (NeurIPS 2016 · 12 citations)
- Actively Learning Hemimetrics with Applications to Eliciting User Preferences (ICML 2016 · 7 citations)
- Vote Until Two of You Agree: Mechanisms with Small Distortion and Sample Complexity (AAAI 2017 · 45 citations)
What has been tried
62 papers here report 321 measured changes (a component added, removed or swapped, compared with a baseline): helped 66%, no clear effect 11%, hurt 17%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add non-uniform coordinate sampling | three of four datasets · sample complexity | Helped | Faster Maximum Inner Product Search in High Dimensions (ICML 2024 · 1 citation) | |
| Use IAT2 instead of AT2, adding log arm count to the challenger index | Best-arm identification · sample complexity | Helped | Optimal Top-Two Method for Best Arm Identification and Fluid Analysis (NeurIPS 2024 · 0 citations) | |
| Use aggressive βt = t² | 2-D Gaussian · generated distribution quality | Helped | Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models (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 35 papers; from OpenAlex and the papers' affiliations).
- Aarhus University · 3 papers
- Carnegie Mellon University · 3 papers
- Google · 3 papers
- Massachusetts Institute of Technology · 3 papers
- Harvard University · 2 papers
- University of Virginia · 2 papers
- National University of Singapore · 2 papers
- Stanford University · 2 papers
- University of Illinois, Urbana Champaign · 2 papers
- Princeton University · 2 papers
Use it
Download BibTeX of 40 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
- Sample complexity of learning distributions (101 papers)
- PAC learnability theory (79 papers)
- Sample complexity of MDPs (42 papers)
Elsewhere in the topic
- Minimax estimation rates (109 papers)
- Optimal mean estimation and subsampling (95 papers)
- Density and property estimation (86 papers)
- Statistical-query lower bounds (85 papers)
- Computational thresholds in graphs and structure (84 papers)
- Learning halfspaces under noise (84 papers)
- Robust and surrogate-loss learning bounds (83 papers)
- Learning under log-concave distributions (80 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).