Privacy guarantees in posterior sampling under contamination

DOI10.1214/26-AOS2628MaRDI QIDQ7317938zbMATH OpenFDO

Authors Shenggang Hu, Louis J. M. Aslett, Hongsheng Dai, Murray Pollock, Gareth O. Roberts

Publication date 24 August 2026

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://projecteuclid.org/journals/annals-of-statistics/volume-54/issue-4/Privacy-guarantees-in-posterior-sampling-under-contamination/10.1214/26-AOS2628.full

Mathematics Subject Classification ID

Bayesian inference (62F15) Generalized linear models (logistic models) (62J12)

Cites work

• Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC
• Concentrated differential privacy: simplifications, extensions, and lower bounds
• Convergence rate of sieve estimates
• Differential privacy for Bayesian inference through posterior sampling
• Exact MCMC with differentially private moves. Exact MCMC with differentially private moves, revisiting the penalty algorithm in a data privacy framework
• Fundamentals of nonparametric Bayesian inference
• Geometrizing rates of convergence under local differential privacy constraints
• scientific article; zbMATH DE number 1350773 (Why is no real title available?)
• scientific article; zbMATH DE number 2038320 (Why is no real title available?)
• scientific article; zbMATH DE number 3232102 (Why is no real title available?)
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Old techniques in differentially private linear regression
• On density estimation at a fixed point under local differential privacy
• On Huber's contaminated model
• On robustness and local differential privacy
• Probabilistic machine learning. An introduction
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
• Rates of convergence of posterior distributions.
• The algorithmic foundations of differential privacy
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• Theory of Cryptography
• Unbiased statistical estimation and valid confidence intervals under differential privacy
• Weak Poincaré inequalities for Markov chains: theory and applications

This page was built for publication: Privacy guarantees in posterior sampling under contamination

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7317938)