INSPECTRE: Privately Estimating the Unseen
Abstract
We develop differentially private methods for estimating various distributional properties. Given a sample from a discrete distribution p, some functional f, and accuracy and privacy parameters alpha and epsilon, the goal is to estimate f(p) up to accuracy alpha, while maintaining epsilon-differential privacy of the sample. We prove almost-tight bounds on the sample size required for this problem for several functionals of interest, including support size, support coverage, and entropy. We show that the cost of privacy is negligible in a variety of settings, both theoretically and experimentally. Our methods are based on a sensitivity analysis of several state-of-the-art methods for estimating these properties with sublinear sample complexities
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jun 05, 2020
- Source ID
- 10.29012/jpc.724
Entities
People
- Gautam Kamath
- Huanyu Zhang
- Jayadev Acharya
- Ziteng Sun
Organizations
- National Science Foundation
- Office of Naval Research