On the Theory and Practice of Privacy-preserving Bayesian Data Analysis
Published in Conference on Uncertainty in Artificial Intelligence, 2016
Recommended citation: Foulds, James, Joseph Geumlek, Max Welling, and Kamalika Chaudhuri (2016). "On the theory and practice of privacy-preserving Bayesian data analysis." Conference on Uncertainty in Artificial Intelligence. https://arxiv.org/abs/1603.07294
This paper explores how posterior sampling, a popular means for Bayesian data analysis, can be performed privately. In particular, it explores the theoretical benefits achieved by adding noise to the sufficient statistics of exponential family models, compared to other approaches that do not leverage these distributional traits. The theory explores the asymptotic relative efficiency of these samples a useful categorization of a mechanisms behavior as data sizes grow.
This work was performed at the University of California San Diego.