DeepAI AI Chat
Log In Sign Up

Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms

by   Jeremy Seeman, et al.
Penn State University

Implementations of the exponential mechanism in differential privacy often require sampling from intractable distributions. When approximate procedures like Markov chain Monte Carlo (MCMC) are used, the end result incurs costs to both privacy and accuracy. Existing work has examined these effects asymptotically, but implementable finite sample results are needed in practice so that users can specify privacy budgets in advance and implement samplers with exact privacy guarantees. In this paper, we use tools from ergodic theory and perfect simulation to design exact finite runtime sampling algorithms for the exponential mechanism by introducing an intermediate modified target distribution using artificial atoms. We propose an additional modification of this sampling algorithm that maintains its ϵ-DP guarantee and has improved runtime at the cost of some utility. We then compare these methods in scenarios where we can explicitly calculate a δ cost (as in (ϵ, δ)-DP) incurred when using standard MCMC techniques. Much as there is a well known trade-off between privacy and utility, we demonstrate that there is also a trade-off between privacy guarantees and runtime.


page 1

page 2

page 3

page 4


Privacy-Aware Rejection Sampling

Differential privacy (DP) offers strong theoretical privacy guarantees, ...

Differentially Private Markov Chain Monte Carlo

Recent developments in differentially private (DP) machine learning and ...

Differentially Private Hamiltonian Monte Carlo

Markov chain Monte Carlo (MCMC) algorithms have long been the main workh...

Optimal Local Bayesian Differential Privacy over Markov Chains

In the literature of data privacy, differential privacy is the most popu...

On Thompson Sampling with Langevin Algorithms

Thompson sampling is a methodology for multi-armed bandit problems that ...

Efficient sampling from the Bingham distribution

We give a algorithm for exact sampling from the Bingham distribution p(x...

Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA

The exponential mechanism is a fundamental tool of Differential Privacy ...