mlsanityData to 7 Oct 2026

A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences

arXiv 2001.05990 ↗First posted 16 Jan 2020cs.IT cs.CR cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R'enyi differential privacy (RDP). Our result is based on the joint range of two f-divergences that underlie the approximate and the R'enyi variations of differential privacy. We apply our result to the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 6; 2023: 2; 2024: 3; 2025: 2.

21 papers.

Sort:

  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. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
  6. 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 42
  7. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  8. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 38
  9. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 27
  10. 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 23
  11. 2021Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFTcited by 20
  12. 2022Distributed Differential Privacy in Multi-Armed Banditscited by 14
9 more
  1. 2023Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protectioncited by 12
  2. 2025Leveraging Randomness in Model and Data Partitioning for Privacy Amplificationcited by 7
  3. 2021Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliabilitycited by 6
  4. 2022The Saddle-Point Accountant for Differential Privacycited by 5
  5. 2022Backpropagation Clipping for Deep Learning with Differential Privacycited by 4
  6. 2024DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharingcited by 3
  7. 2024Laplace Transform Interpretation of Differential Privacycited by 1
  8. 2022The Poisson binomial mechanism for secure and private federated learningcited by 0
  9. 2025Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)cited by 0