Timezone: »

INSPECTRE: Privately Estimating the Unseen
Jayadev Acharya · Gautam Kamath · Ziteng Sun · Huanyu Zhang

Wed Jul 11 09:15 AM -- 12:00 PM (PDT) @ Hall B #59

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

Author Information

Jayadev Acharya (Cornell University)
Gautam Kamath (MIT)
Ziteng Sun (Cornell University)
Huanyu Zhang (Cornell University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors