mlsanityData to 7 Oct 2026

Concentrated Differential Privacy

arXiv 1603.01887 ↗First posted 6 Mar 2016cs.DS cs.CRcited by 139

Not on the map. Why?

Abstract (arXiv)

We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without compromising on cumulative privacy loss over multiple computations.

Key facts. Cited by 139 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 26; 2023: 28; 2024: 26; 2025: 18; 2026: 6.

139 papers.

Sort:

By area:

  1. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  2. 2021Numerical Composition of Differential Privacycited by 174
  3. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  4. 2023Privacy Auditing with One (1) Training Runcited by 119
  5. 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
  6. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
  7. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
  8. 2022Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Losscited by 60
  9. 2022Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streamscited by 59
  10. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 58
  11. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 51
  12. 2023Privacy-Preserving In-Context Learning for Large Language Modelscited by 50
38 more
  1. 2021Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Datacited by 47
  2. 2021Covariance-Aware Private Mean Estimation Without Private Covariance Estimationcited by 46
  3. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  4. 2023Faster high-accuracy log-concave sampling via algorithmic warm startscited by 44
  5. 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 42
  6. 2024Private Fine-tuning of Large Language Models with Zeroth-order Optimizationcited by 41
  7. 2021Leveraging Public Data for Practical Private Query Releasecited by 39
  8. 2021Private and polynomial time algorithms for learning Gaussians and beyondcited by 39
  9. 2022Privately Fine-Tuning Large Language Models with Differential Privacycited by 39
  10. 2021Fast and Memory Efficient Differentially Private-SGD via JL Projectionscited by 29
  11. 2021Federated f-Differential Privacycited by 29
  12. 2022Stronger Privacy Amplification by Shuffling for R'enyi and Approximate Differential Privacycited by 29
  13. 2021Lossless Compression of Efficient Private Local Randomizerscited by 27
  14. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  15. 2021Differentially Private SGD with Non-Smooth Lossescited by 22
  16. 2021Differentially Private Quantilescited by 22
  17. 2022Fully Adaptive Composition in Differential Privacycited by 22
  18. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  19. 2022Offline Reinforcement Learning with Differential Privacycited by 19
  20. 2023Unleashing the Power of Randomization in Auditing Differentially Private MLcited by 19
  21. 2023Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuationcited by 19
  22. 2023Generating Private Synthetic Data with Genetic Algorithmscited by 18
  23. 2021Local Differential Privacy Is Equivalent to Contraction of Eγ-Divergencecited by 17
  24. 2021On the Renyi Differential Privacy of the Shuffle Modelcited by 16
  25. 2021Oneshot Differentially Private Top-k Selectioncited by 16
  26. 2021SGDE: Secure Generative Data Exchange for Cross-Silo Federated Learningcited by 15
  27. 2022Edgeworth Accountant: An Analytical Approach to Differential Privacy Compositioncited by 14
  28. 2022Faster Privacy Accounting via Evolving Discretizationcited by 14
  29. 2022DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Samplingcited by 13
  30. 2023Faster Differentially Private Convex Optimization via Second-Order Methodscited by 13
  31. 2023Flow-based Distributionally Robust Optimizationcited by 13
  32. 2023Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacycited by 13
  33. 2024Balls-and-Bins Sampling for DP-SGDcited by 13
  34. 2023A Bias-Accuracy-Privacy Trilemma for Statistical Estimationcited by 12
  35. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  36. 2024Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Compositioncited by 12
  37. 2024Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimationcited by 11
  38. 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacycited by 11

50 most cited of 139 All 139 (JSON)