mlsanityData to 14 Oct 2026

FriendlyCore: Practical Differentially Private Aggregation

arXiv 2110.10132 ↗First posted 19 Oct 2021cs.LG cs.DScited by 34

Not on the map. Why?

Abstract (arXiv)

Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results. We propose a simple and practical tool, mathsfFriendlyCore, that takes a set of points cal D from an unrestricted (pseudo) metric space as input. When cal D has effective diameter r, mathsfFriendlyCore returns a "stable" subset cal C subseteq cal D that includes all points, except possibly few outliers, and is em certified to have diameter r. mathsfFriendlyCore can be used to preprocess the input before privately aggregating it, potentially simplifying the aggregation or boosting its accuracy. Surprisingly, mathsfFriendlyCore is light-weight with no dependence on the dimension. We empirically demonstrate its advantages in boosting the accuracy of mean estimation and clustering tasks such as k-means and k-GMM, outperforming tailored methods.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 15 of its 44 references that are in the map. First posted on arXiv 19 Oct 2021.

Builds on

15 of 44 references.

References · 15

  1. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
  2. 2017Finite Sample Differentially Private Confidence Intervalscited by 104
  3. 2018Privately Learning High-Dimensional Distributionscited by 104
  4. 2020CoinPress: Practical Private Mean and Covariance Estimationcited by 74
  5. 2020Private Mean Estimation of Heavy-Tailed Distributionscited by 73
  6. 2021Learning with User-Level Privacycited by 72
  7. 2015Differentially Private Release and Learning of Threshold Functionscited by 60
  8. 2019Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimationcited by 52
  9. 2021Instance-optimal Mean Estimation Under Differential Privacycited by 37
  10. 2019Privately Learning Thresholds: Closing the Exponential Gapcited by 31
  11. 2019Differentially Private Algorithms for Learning Mixtures of Separated Gaussianscited by 27
  12. 2016Locating a Small Cluster Privatelycited by 20
3 more
  1. 2020Differentially Private Confidence Intervalscited by 20
  2. 2021Privately Learning Subspacescited by 16
  3. 2021Differentially Private Algorithms for Clustering with Stability Assumptionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 2; 2023: 14; 2024: 7; 2025: 6; 2026: 1.

34 papers.

Sort:

  1. 2021Private and polynomial time algorithms for learning Gaussians and beyondcited by 39
  2. 2021Private Robust Estimation by Stabilizing Convex Relaxationscited by 38
  3. 2021A Private and Computationally-Efficient Estimator for Unbounded Gaussianscited by 34
  4. 2023From Robustness to Privacy and Backcited by 27
  5. 2021Tight and Robust Private Mean Estimation with Few Userscited by 26
  6. 2023Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributionscited by 22
  7. 2023Private estimation algorithms for stochastic block models and mixture modelscited by 21
  8. 2023Polynomial Time and Private Learning of Unbounded Gaussian Mixture Modelscited by 19
  9. 2023Better and Simpler Lower Bounds for Differentially Private Statistical Estimationcited by 17
  10. 2023Private Distribution Learning with Public Data: The View from Sample Compressioncited by 14
  11. 2023A Bias-Accuracy-Privacy Trilemma for Statistical Estimationcited by 12
  12. 2023User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Ratescited by 12
22 more
  1. 2024Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimescited by 9
  2. 2023Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codescited by 8
  3. 2024Insufficient Statistics Perturbation: Stable Estimators for Private Least Squarescited by 7
  4. 2024Dimension-free Private Mean Estimation for Anisotropic Distributionscited by 6
  5. 2023A Polynomial Time, Pure Differentially Private Estimator for Binary Product Distributionscited by 5
  6. 2023Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samplescited by 5
  7. 2024Faster Algorithms for User-Level Private Stochastic Convex Optimizationcited by 4
  8. 2025Urania: Differentially Private Insights into AI Usecited by 4
  9. 2023Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivitycited by 3
  10. 2024Not All Learnable Distribution Classes are Privately Learnablecited by 3
  11. 2024Private Geometric Mediancited by 3
  12. 2025Tukey Depth Mechanisms for Practical Private Mean Estimationcited by 2
  13. 2023The Relative Gaussian Mechanism and its Application to Private Gradient Descentcited by 1
  14. 2024On Differentially Private Subspace Estimation in a Distribution-Free Settingcited by 1
  15. 2025Improved subsample-and-aggregate via the private modified winsorized meancited by 1
  16. 2025Private Geometric Median in Nearly-Linear Timecited by 1
  17. 2025Privately Estimating Black-Box Statisticscited by 1
  18. 2026On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCAcited by 1
  19. 2022Differentially-Private Bayes Consistencycited by 0
  20. 2022Privately Estimating a Gaussian: Efficient, Robust and Optimalcited by 0
  21. 2023Instance-Specific Asymmetric Sensitivity in Differential Privacycited by 0
  22. 2025Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regressioncited by 0