Research map / Learning theory and algorithms / Sample complexity
Computational thresholds in graphs and structure
Studies low-degree evidence and algorithms for community detection, structure learning and graph search.
84 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Sample complexity, keyword cluster “al · bounds · et”
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.
15 papers in 2023–24 and 22 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.5% to 6.7%.
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 · Exact Exponent in Optimal Rates for Crowdsourcing (ICML 2016 · 29 citations)
- 2017 · Phase Transitions for Scale-Free SAT Formulas (AAAI 2017 · 16 citations)
- 2018 · Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling (NeurIPS 2018 · 13 citations)
- 2019 · Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models (NeurIPS 2019 · 5 citations)
- 2020 · Linear Lower Bounds and Conditioning of Differentiable Games (ICML 2020 · 25 citations)
- 2021 · Proportional Representation under Single-Crossing Preferences Revisited (AAAI 2021 · 7 citations)
- 2022 · The Query Complexity of Cake Cutting (NeurIPS 2022 · 16 citations)
- 2023 · From Understanding the Population Dynamics of the NSGA-II to the First Proven Lower Bounds (AAAI 2023 · 50 citations)
- 2024 · Identification for Tree-Shaped Structural Causal Models in Polynomial Time (AAAI 2024 · 1 citation)
- 2025 · Consistent Query Answering over Existential Rules with Open and Closed Predicates (AAAI 2025 · 0 citations)
- 2026 · Matroid Algorithms Under Size-Sensitive Independence Oracles (ICML 2026 · 0 citations)
Earliest papers here
- Exact Exponent in Optimal Rates for Crowdsourcing (ICML 2016 · 29 citations)
- Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation (NeurIPS 2016 · 23 citations)
- Optimality of Belief Propagation for Crowdsourced Classification (ICML 2016 · 13 citations)
What has been tried
55 papers here report 315 measured changes (a component added, removed or swapped, compared with a baseline): helped 65%, no clear effect 10%, hurt 19%, 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 |
|---|---|---|---|---|
| discard vertices from the predefined sample according to the algorithm | CollegeMsg · objective ratio to offline pivot | Helped | Sampling for Beyond-Worst-Case Online Ranking (AAAI 2024 · 0 citations) | |
| Sort candidate neighbors before pruning | SIFT1M (at 99% recall) · QPS | 5% higher QPS | Helped | Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs (ICML 2025) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 37 papers; from OpenAlex and the papers' affiliations).
- Czech Technical University in Prague · 2 papers
- Northwestern University · 2 papers
- Google · 2 papers
- Technion - Israel Institute of Technology · 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
- Statistical-query lower bounds (85 papers)
- Robust and surrogate-loss learning bounds (83 papers)
- Generalization and limits under data constraints (72 papers)
Elsewhere in the topic
- Minimax estimation rates (109 papers)
- Sample complexity of learning distributions (101 papers)
- Optimal mean estimation and subsampling (95 papers)
- Density and property estimation (86 papers)
- Learning halfspaces under noise (84 papers)
- Sample complexity of ranking and selection (80 papers)
- Learning under log-concave distributions (80 papers)
- PAC learnability theory (79 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).