A. Bharadwaj and G. Cormode. Sample-and-threshold differential privacy: Histograms and applications. In Privacy in Machine Learning (NeurIPS workshop), 2021. (workshop version).

Federated analytics aims to compute accurate statistics from distributed datasets. A “Differential Privacy” (DP) guarantee is usually desired by the users of the devices storing the data. In this work, we prove a strong (ε, δ)-DP guarantee for a highly practical sampling-based procedure to derive histograms. We also provide accuracy guarantees and show how to apply the procedure to estimate quantiles and modes.

[ bib | video | poster | .pdf ] Back

This file was generated by bibtex2html 1.92.