mlsanityData to 14 Oct 2026

Privacy Amplification Via Bernoulli Sampling

arXiv 2105.10594 ↗First posted 21 May 2021cs.LG cs.CR cs.ITcited by 4

Not on the map. Why?

Abstract (arXiv)

Balancing privacy and accuracy is a major challenge in designing differentially private machine learning algorithms. One way to improve this tradeoff for free is to leverage the noise in common data operations that already use randomness. Such operations include noisy SGD and data subsampling. The additional noise in these operations may amplify the privacy guarantee of the overall algorithm, a phenomenon known as privacy amplification. In this paper, we analyze the privacy amplification of sampling from a multidimensional Bernoulli distribution family given the parameter from a private algorithm. This setup has applications to Bayesian inference and to data compression. We provide an algorithm to compute the amplification factor, and we establish upper and lower bounds on this factor.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

15 of 32 references.

References · 15

  1. 2017Renyi Differential Privacycited by 650
  2. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  3. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 242
  4. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 236
  5. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 204
  6. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  7. 2018Privacy Amplification by Iterationcited by 100
  8. 2019The Privacy Blanket of the Shuffle Modelcited by 74
  9. 2015Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlocited by 63
  10. 2015Differentially Private Release and Learning of Threshold Functionscited by 60
  11. 2016On the Theory and Practice of Privacy-Preserving Bayesian Data Analysiscited by 35
  12. 2019Privacy Amplification by Mixing and Diffusion Mechanismscited by 21
3 more
  1. 2014Characterizing the Sample Complexity of Private Learnerscited by 19
  2. 2013Bayesian Differential Privacy through Posterior Samplingcited by 18
  3. 2017R'enyi Differential Privacy Mechanisms for Posterior Samplingcited by 16

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 2.

4 papers.

  1. 2022Sparse Random Networks for Communication-Efficient Federated Learningcited by 32
  2. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  3. 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Modelscited by 3
  4. 2025Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Maskingcited by 0