mlsanityData to 14 Oct 2026

AdaCliP: Adaptive Clipping for Private SGD

arXiv 1908.07643 ↗First posted 20 Aug 2019cs.LG cs.CR stat.MLcited by 77

Not on the map. Why?

Abstract (arXiv)

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive clipping of the gradient. We empirically demonstrate that AdaCliP reduces the amount of added noise and produces models with better accuracy.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 20; 2023: 13; 2024: 6; 2025: 12; 2026: 7.

77 papers.

Sort:

By area:

  1. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 412
  2. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  3. 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 170
  4. 2021Large-Scale Differentially Private BERTcited by 118
  5. 2021Label Leakage and Protection in Two-party Split Learningcited by 90
  6. 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 88
  7. 2022Toward Training at ImageNet Scale with Differential Privacycited by 87
  8. 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
  9. 2023Toward Understanding Why Adam Converges Faster Than SGD for Transformerscited by 53
  10. 2022Exploring the Limits of Differentially Private Deep Learning with Group-wise Clippingcited by 52
  11. 2022Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)cited by 48
  12. 2021Private Adaptive Gradient Methods for Convex Optimizationcited by 46
38 more
  1. 2022Large Scale Transfer Learning for Differentially Private Image Classificationcited by 41
  2. 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
  3. 2022Private Adaptive Optimization with Side Informationcited by 38
  4. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  5. 2022Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimizationcited by 36
  6. 2021DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregationcited by 31
  7. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  8. 2021Dynamic Differential-Privacy Preserving SGDcited by 30
  9. 2024SeqMIA: Sequential-Metric Based Membership Inference Attackcited by 23
  10. 2022Differentially Private Learning with Per-Sample Adaptive Clippingcited by 21
  11. 2021DPNAS: Neural Architecture Search for Deep Learning with Differential Privacycited by 20
  12. 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
  13. 2022Nonlinear gradient mappings and stochastic optimization: A general framework with applications to heavy-tail noisecited by 16
  14. 2022Differentially Private Covariance Revisitedcited by 15
  15. 2023Securing Distributed SGD against Gradient Leakage Threatscited by 14
  16. 2023Fast Optimal Locally Private Mean Estimation via Random Projectionscited by 14
  17. 2022DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Samplingcited by 13
  18. 2022Adap DP-FL: Differentially Private Federated Learning with Adaptive Noisecited by 13
  19. 2023DPMLBench: Holistic Evaluation of Differentially Private Machine Learningcited by 13
  20. 2024Adaptive Gradient Clipping for Robust Federated Learningcited by 11
  21. 2021Differentially Private Coordinate Descent for Composite Empirical Risk Minimizationcited by 10
  22. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 10
  23. 2023Differentially Private Video Activity Recognitioncited by 9
  24. 2021Improving Differentially Private SGD via Randomly Sparsified Gradientscited by 8
  25. 2022Differentially Private Image Classification from Featurescited by 7
  26. 2023Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embeddingcited by 7
  27. 2024To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensionscited by 7
  28. 2022(Nearly) Optimal Private Linear Regression via Adaptive Clippingcited by 6
  29. 2022Private Ad Modeling with DP-SGDcited by 6
  30. 2023PLAN: Variance-Aware Private Mean Estimationcited by 6
  31. 2023Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filteringcited by 6
  32. 2025DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimationcited by 6
  33. 2021Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descentcited by 5
  34. 2021Efficient Hyperparameter Optimization for Differentially Private Deep Learningcited by 5
  35. 2021Adaptive Differentially Private Empirical Risk Minimizationcited by 5
  36. 2022Dynamic Global Sensitivity for Differentially Private Contextual Banditscited by 5
  37. 2024Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tailscited by 5
  38. 2025Differentially Private Federated Learning With Time-Adaptive Privacy Spendingcited by 5

50 most cited of 77 All 77 (JSON)