mlsanityData to 7 Oct 2026

Subsampled R'enyi Differential Privacy and Analytical Moments Accountant

arXiv 1808.00087 ↗First posted 31 Jul 2018cs.LG cs.CR stat.MLcited by 234

Not on the map. Why?

Abstract (arXiv)

We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the R'enyi Differential Privacy (RDP) (Mironov, 2017) parameters for algorithms that: (1) subsample the dataset, and then (2) applies a randomized mechanism M to the subsample, in terms of the RDP parameters of M and the subsampling probability parameter. Our results generalize the moments accounting technique, developed by Abadi et al. (2016) for the Gaussian mechanism, to any subsampled RDP mechanism.

Key facts. Cited by 234 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 52; 2023: 42; 2024: 24; 2025: 39; 2026: 31.

234 papers.

Sort:

By area:

  1. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  2. 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 169
  3. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  4. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  5. 2023Privacy Auditing with One (1) Training Runcited by 119
  6. 2021Large Scale Private Learning via Low-rank Reparametrizationcited by 87
  7. 2022Toward Training at ImageNet Scale with Differential Privacycited by 87
  8. 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 87
  9. 2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
  10. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 83
  11. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  12. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
38 more
  1. 2021Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descentcited by 71
  2. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  3. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecturecited by 63
  4. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  5. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 51
  6. 2022Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learningcited by 48
  7. 2022Differentially Private Bias-Term Fine-tuning of Foundation Modelscited by 47
  8. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  9. 2021Zero-Shot Recommender Systemscited by 45
  10. 2022Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)cited by 45
  11. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  12. 2022Bounding Training Data Reconstruction in Private (Deep) Learningcited by 43
  13. 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 42
  14. 2021Gradient-Leakage Resilient Federated Learningcited by 40
  15. 2022Large Scale Transfer Learning for Differentially Private Image Classificationcited by 40
  16. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  17. 2022Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimizationcited by 35
  18. 2022Private Set Generation with Discriminative Informationcited by 34
  19. 2021DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentationscited by 33
  20. 2021Releasing Graph Neural Networks with Differential Privacy Guaranteescited by 32
  21. 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
  22. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  23. 2022Sparse Random Networks for Communication-Efficient Federated Learningcited by 32
  24. 2021Dynamic Differential-Privacy Preserving SGDcited by 29
  25. 2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
  26. 2023DP-LDMs: Differentially Private Latent Diffusion Modelscited by 28
  27. 2022CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learningcited by 24
  28. 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
  29. 2021PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learningcited by 23
  30. 2022Differentially Private SGDA for Minimax Problemscited by 23
  31. 2022Fully Adaptive Composition in Differential Privacycited by 22
  32. 2021Hermite Polynomial Features for Private Data Generationcited by 21
  33. 2021Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFTcited by 20
  34. 2021DPNAS: Neural Architecture Search for Deep Learning with Differential Privacycited by 20
  35. 2022Individual Privacy Accounting for Differentially Private Stochastic Gradient Descentcited by 20
  36. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  37. 2021Differentially Private Sliced Wasserstein Distancecited by 19
  38. 2022Individual Privacy Accounting with Gaussian Differential Privacycited by 19

50 most cited of 234 All 234 (JSON)