English

Privacy Amplification Via Bernoulli Sampling

Machine Learning 2021-10-20 v2 Cryptography and Security Information Theory math.IT

Abstract

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.

Keywords

Cite

@article{arxiv.2105.10594,
  title  = {Privacy Amplification Via Bernoulli Sampling},
  author = {Jacob Imola and Kamalika Chaudhuri},
  journal= {arXiv preprint arXiv:2105.10594},
  year   = {2021}
}

Comments

11 pages, 3 figures. Appeared in TPDP Workshop @ ICML 2021

R2 v1 2026-06-24T02:21:35.758Z