AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differential Privacy Over Riemannian Manifolds

Matthew Reimherr, Karthik Bharath, Carlos J Soto

NeurIPS 2021 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
privatize via intrinsic Riemannian Laplace instead of ambient Euclidean LaplaceFrechet mean privatization · SPDM P(k)Euclidean distance between mean and private meanImproved
privatize via intrinsic Riemannian Laplace instead of ambient Euclidean LaplaceFrechet mean privatization · Sphere S^2average Euclidean distance (noise): 16.8%Improved
privatize via intrinsic Riemannian Laplace instead of ambient Euclidean Laplace at larger sample sizesFrechet mean privatization · Sphere S^2average Euclidean distance (noise): 12%Improved
use ambient Euclidean embedding instead of intrinsic mechanismSPDM private mean · SPDM P(2), sample sizes 20-40fraction valid on manifold: 25%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy