Bias and Variance of Post-processing in Differential Privacy
Zhu, Keyu, Van Hentenryck, Pascal, Fioretto, Ferdinando
–arXiv.org Artificial Intelligence
Post-processing immunity is a fundamental property of differential privacy: it enables the application of arbitrary data-independent transformations to the results of differentially private outputs without affecting their privacy guarantees. When query outputs must satisfy domain constraints, post-processing can be used to project the privacy-preserving outputs onto the feasible region. Moreover, when the feasible region is convex, a widely adopted class of post-processing steps is also guaranteed to improve accuracy. Post-processing has been applied successfully in many applications including census data-release, energy systems, and mobility. However, its effects on the noise distribution is poorly understood: It is often argued that post-processing may introduce bias and increase variance. This paper takes a first step towards understanding the properties of post-processing. It considers the release of census data and examines, both theoretically and empirically, the behavior of a widely adopted class of post-processing functions.
arXiv.org Artificial Intelligence
Oct-8-2020
- Country:
- Europe (0.14)
- North America > United States
- Texas (0.04)
- Arizona (0.04)
- New Mexico (0.04)
- Genre:
- Research Report (0.50)
- Industry:
- Technology: