Google Research

Tight Bounds for Differentially Private Anonymized Histograms

SOSA 2022

Abstract

In this note, we consider the problem of differentially privately (DP) computing an anonymoized histogram, which is defined as the multiset of counts of the input dataset (without bucket labels). In the low-privacy regime ε ≥ 1, we give an ε-DP algorithm with an l1-error bound of O(√n/e^ε). In the high-privacy regime ε < 1, we give an Ω(sqrt(n log(1/ε)/ε)) lower bound on the l1 error. In both cases, our bounds asymptotically match the previously known lower/upper bounds due to [Suresh, NeurIPS 2019].

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work