Skip to main content

Research Repository

Advanced Search

Differential privacy over Riemannian manifolds

Reimherr, Matthew; Bharath, Karthik; Soto, Carlos

Differential privacy over Riemannian manifolds Thumbnail


Matthew Reimherr

Carlos Soto


In this work we consider the problem of releasing a differentially private statistical summary that resides on a Riemannian manifold. We present an extension of the Laplace or K-norm mechanism that utilizes intrinsic distances and volumes on the manifold. We also consider in detail the specific case where the summary is the Frechet mean of data residing on a manifold. We demonstrate that our mechanism is rate optimal and depends only on the dimension of the manifold, not on the dimension of any ambient space, while also showing how ignoring the manifold structure can decrease the utility of the sanitized summary. We illustrate our framework in two examples of particular interest in statistics: the space of symmetric positive definite matrices, which is used for covariance matrices, and the sphere, which can be used as a space for modeling discrete distributions.

Conference Name Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)
Conference Location Online
Start Date Dec 7, 2021
End Date Dec 10, 2021
Acceptance Date Sep 28, 2021
Online Publication Date Dec 10, 2021
Publication Date Dec 10, 2021
Deposit Date Oct 26, 2021
Publicly Available Date Dec 10, 2021
Public URL
Publisher URL
Related Public URLs


You might also like

Downloadable Citations