DeepAI AI Chat
Log In Sign Up

Rényi Differential Privacy Mechanisms for Posterior Sampling

by   Joseph Geumlek, et al.
University of California, San Diego

Using a recently proposed privacy definition of Rényi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating the influence of individual data points. In particular, we focus on sampling from an exponential family and specific generalized linear models, such as logistic regression. We propose novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework. Each method is capable of achieving arbitrary RDP privacy guarantees, and we offer experimental results of their efficacy.


page 1

page 2

page 3

page 4


Bayesian Differential Privacy through Posterior Sampling

Differential privacy formalises privacy-preserving mechanisms that provi...

Differential Privacy of Dirichlet Posterior Sampling

Besides the Laplace distribution and the Gaussian distribution, there ar...

Differential Privacy for Sparse Classification Learning

In this paper, we present a differential privacy version of convex and n...

Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

This paper investigates the problem of regret minimization for multi-arm...

Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT

The recently proposed Fast Fourier Transform (FFT)-based accountant for ...

A New Analysis of Differential Privacy's Generalization Guarantees

We give a new proof of the "transfer theorem" underlying adaptive data a...

Variational Bayes In Private Settings (VIPS)

We provide a general framework for privacy-preserving variational Bayes ...