Research map / Federated learning and privacy / Differential privacy
Local-DP and private estimation
Estimate means and statistics under local or central privacy with minimax rates.
113 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Differential privacy, keyword cluster “estimation · error · algorithms”
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.
28 papers in 2023–24 and 32 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 13.0% to 12.0%.
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 · Discrete Distribution Estimation under Local Privacy (ICML 2016 · 210 citations)
- 2017 · Priv’IT: Private and Sample Efficient Identity Testing (ICML 2017 · 11 citations)
- 2018 · Differentially Private Testing of Identity and Closeness of Discrete Distributions (NeurIPS 2018 · 42 citations)
- 2019 · On Sparse Linear Regression in the Local Differential Privacy Model (ICML 2019 · 44 citations)
- 2020 · CoinPress: Practical Private Mean and Covariance Estimation (NeurIPS 2020 · 25 citations)
- 2021 · Leveraging Public Data for Practical Private Query Release (ICML 2021 · 18 citations)
- 2022 · Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data (ICML 2022 · 12 citations)
- 2023 · Differentially Private Nonlinear Causal Discovery from Numerical Data (AAAI 2023 · 5 citations)
- 2024 · Exactly Minimax-Optimal Locally Differentially Private Sampling (NeurIPS 2024 · 1 citation)
- 2025 · Sum Estimation under Personalized Local Differential Privacy (NeurIPS 2025 · 1 citation)
- 2026 · Accurate, Private, Secure, Federated U-statistics with Higher Degree (ICML 2026 · 0 citations)
Earliest papers here
- Discrete Distribution Estimation under Local Privacy (ICML 2016 · 210 citations)
- Wishart Mechanism for Differentially Private Principal Components Analysis (AAAI 2016 · 52 citations)
- On the Differential Privacy of Bayesian Inference (AAAI 2016 · 37 citations)
What has been tried
79 papers here report 496 measured changes (a component added, removed or swapped, compared with a baseline): helped 66%, no clear effect 9%, hurt 18%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add the soft-thresholding operator | NLDP, k-sparse sub-Gaussian · ℓ2 estimation error upper bound | \tilde{O}(\frac{d^{\frac{3}{2}}}{\sqrt{n}\epsilon}) versus \tilde{O}(\frac{d\sqrt{k}}{\sqrt{n}\epsilon}) | Helped | Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model (ICLR 2024 · 0 citations) |
| replace hourglass noise with independent Laplace noise | Add-remove mean estimation, high privacy · MSE | \frac{2(u-l)^2}{|D|^2\varepsilon^2} \left( 1 + o(1)\right) | Hurt | Mean Estimation in the Add-Remove Model of Differential Privacy (ICML 2024 · 0 citations) |
| Increase ε | Simulation experiments · utility | Helped | On the Computational Complexity of Private High-dimensional Model Selection (NeurIPS 2024 · 0 citations) | |
| Use G=F instead of uniform sampling | U(0, 1), n=103, r=0.5 · maximum absolute error | 0.183 -> 0.183 | No clear effect | Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy (ICML 2024) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 60 papers; from OpenAlex and the papers' affiliations).
- Google · 7 papers
- University of Copenhagen · 4 papers
- Duke University · 3 papers
- University of Alberta · 3 papers
- Tsinghua University · 3 papers
- Carnegie Mellon University · 3 papers
- Copenhagen University · 3 papers
- Stanford University · 3 papers
- University at Buffalo · 2 papers
- State University of New York at Buffalo · 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
- Privacy accounting and mechanisms (127 papers)
- Private online and user-level learning (116 papers)
- Private data analysis frameworks (105 papers)
- Differentially private clustering (41 papers)
Elsewhere in the topic
- Private training with public data (96 papers)
- Differentially private synthetic data (81 papers)
- DP-SGD refinements (60 papers)
- Differentially private federated learning (35 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).