Lower Bounds for Differential Privacy from Gaussian Width

TL;DR

This paper establishes lower bounds on the sample complexity for differentially private linear query workloads using Gaussian width, providing a geometric perspective that characterizes when Gaussian noise mechanisms are optimal.

Contribution

It introduces Gaussian width as a key geometric measure for sensitivity polytopes, leading to tight lower bounds and characterizations of optimal mechanisms in differential privacy.

Findings

Gaussian width determines lower bounds on sample complexity

Characterization of workloads where Gaussian noise is optimal

Alternative proof of Pisier's Volume Number Theorem

Abstract

We study the optimal sample complexity of a given workload of linear queries under the constraints of differential privacy. The sample complexity of a query answering mechanism under error parameter $\alpha$ is the smallest $n$ such that the mechanism answers the workload with error at most $\alpha$ on any database of size $n$. Following a line of research started by Hardt and Talwar [STOC 2010], we analyze sample complexity using the tools of asymptotic convex geometry. We study the sensitivity polytope, a natural convex body associated with a query workload that quantifies how query answers can change between neighboring databases. This is the information that, roughly speaking, is protected by a differentially private algorithm, and, for this reason, we expect that a "bigger" sensitivity polytope implies larger sample complexity. Our results identify the mean Gaussian width as an appropriate measure of the size of the polytope, and show sample complexity lower bounds in terms of this quantity. Our lower bounds completely characterize the workloads for which the Gaussian noise mechanism is optimal up to constants as those having asymptotically maximal Gaussian width. Our techniques also yield an alternative proof of Pisier's Volume Number Theorem which also suggests an approach to improving the parameters of the theorem.