ICML2025Top-tier venue

Approximate Differential Privacy of the ℓ2 Mechanism

Matthew Joseph, Alex Kulesza, Alexander Yu

2025Year

1Top-tier citations

Abstract

We study the 2 mechanism for computing a ddimensional statistic with bounded 2 sensitivity under approximate differential privacy. Across a range of privacy parameters, we find that the 2 mechanism obtains lower error than the Laplace and Gaussian mechanisms, matching the former at d = 1 and approaching the latter as d → ∞.

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

What it claims
Who builds on it
How it compares
Where it falls short

You ask

Your agent calls

Luneget_paper_fulltext

Free to start. No credit card required.

Terminal

Install the CLI

$ lune papers fulltext 1121aef8-62aa-4194-bee1-79cfd403be5d

Cited by top-tier papers1

Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential PrivacyAlexander Bienstock, Antigoni Polychroniadou, Yu WeiICML 2026

Ask how each one uses it

Builds on5

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines