mlsanityData to 14 Oct 2026

Differentially Private Markov Chain Monte Carlo

arXiv 1901.10275 ↗First posted 29 Jan 2019stat.ML cs.CR cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learning by presenting the first general DP Markov chain Monte Carlo (MCMC) algorithm whose privacy-guarantees are not subject to unrealistic assumptions on Markov chain convergence and that is applicable to posterior inference in arbitrary models. Our algorithm is based on a decomposition of the Barker acceptance test that allows evaluating the R'enyi DP privacy cost of the accept-reject choice. We further show how to improve the DP guarantee through data subsampling and approximate acceptance tests.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 5; 2023: 5; 2024: 3; 2025: 2.

18 papers.

Sort:

  1. 2022Noise-Aware Statistical Inference with Differentially Private Synthetic Datacited by 9
  2. 2021Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliabilitycited by 6
  3. 2023Protect Your Score: Contact Tracing With Differential Privacy Guaranteescited by 5
  4. 2021Gaussian Processes with Differential Privacycited by 3
  5. 2022Statistic Selection and MCMC for Differentially Private Bayesian Estimationcited by 3
  6. 2022Sharper Utility Bounds for Differentially Private Modelscited by 3
  7. 2023DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inferencecited by 3
  8. 2022Differentially private partitioned variational inferencecited by 2
  9. 2021Locally Differentially Private Bayesian Inferencecited by 1
  10. 2023Differentially Private Online Bayesian Estimation With Adaptive Truncationcited by 1
  11. 2023Differentially Private Distributed Bayesian Linear Regression with MCMCcited by 1
  12. 2023Differentially Private Statistical Inference through β-Divergence One Posterior Samplingcited by 1
6 more
  1. 2024Differentially private Bayesian testscited by 1
  2. 2022Robust One Round Federated Learning with Predictive Space Bayesian Inferencecited by 0
  3. 2024Noise-Aware Differentially Private Variational Inferencecited by 0
  4. 2024Federated and differentially private estimation of KL divergencecited by 0
  5. 2025Differential privacy guarantees of Markov chain Monte Carlo algorithmscited by 0
  6. 2025Differentially Private Geodesic Regressioncited by 0