Research map / Learning theory and algorithms / Sample complexity
Private and query-efficient algorithms
Gives sample, space and query complexity bounds for private optimization and approximation.
70 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Sample complexity, keyword cluster “epsilon · log · tilde”
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.
23 papers in 2023–24 and 22 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 6.9% 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 · Faster Eigenvector Computation via Shift-and-Invert Preconditioning (ICML 2016 · 32 citations)
- 2017 · Maximum Selection and Ranking under Noisy Comparisons (ICML 2017 · 22 citations)
- 2018 · Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model (NeurIPS 2018 · 85 citations)
- 2020 · A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model (ICML 2020 · 3 citations)
- 2021 · Distributed Saddle-Point Problems Under Data Similarity (NeurIPS 2021 · 14 citations)
- 2022 · Faster and Scalable Algorithms for Densest Subgraph and Decomposition (NeurIPS 2022 · 3 citations)
- 2023 · Markov Decision Processes with Time-Varying Geometric Discounting (AAAI 2023 · 1 citation)
- 2024 · Truncated Variance Reduced Value Iteration (NeurIPS 2024 · 1 citation)
- 2025 · On Fine-Grained Distinct Element Estimation (ICML 2025 · 0 citations)
- 2026 · Incremental BPE Tokenization (ICML 2026 · 0 citations)
Earliest papers here
- Faster Eigenvector Computation via Shift-and-Invert Preconditioning (ICML 2016 · 32 citations)
- Minimizing Quadratic Functions in Constant Time (NeurIPS 2016 · 4 citations)
- Maximum Selection and Ranking under Noisy Comparisons (ICML 2017 · 22 citations)
What has been tried
53 papers here report 262 measured changes (a component added, removed or swapped, compared with a baseline): helped 71%, no clear effect 9%, hurt 16%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Set δ = -γ instead of δ = 0 | Continual counting, t > 2^10 · variance | Helped | Private Continual Counting of Unbounded Streams (NeurIPS 2025 · 0 citations) | |
| Increase λ | Empirical privacy loss at large elapsed time d · privacy loss | Hurt | Continual Counting with Gradual Privacy Expiration (NeurIPS 2024 · 0 citations) | |
| Initialize each inner process with the momentum iterate | com-dblp · outer-loop iterations | Helped | Accelerated Evolving Set Processes for Local PageRank Computation (NeurIPS 2025) | |
| replace the original initialization with an unrelated random initialization | MNIST, SVHN, CIFAR10, and CIFAR100 · test error monotonicity | No clear effect | MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation (ICML 2024) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 45 papers; from OpenAlex and the papers' affiliations).
- Google · 8 papers
- Stanford University · 4 papers
- Carnegie Mellon University · 4 papers
- Yale University · 3 papers
- Peking University · 3 papers
- Nanjing University · 3 papers
- Virginia Polytechnic Institute and State University · 2 papers
- Virginia Tech · 2 papers
- Meta · 2 papers
- University of Copenhagen · 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
- Learning halfspaces under noise (84 papers)
- Learning under log-concave distributions (80 papers)
- Coresets and sublinear estimation (35 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)
- Statistical-query lower bounds (85 papers)
- Computational thresholds in graphs and structure (84 papers)
- Robust and surrogate-loss learning bounds (83 papers)
- Sample complexity of ranking and selection (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).