Differential Privacy Over Riemannian Manifolds

11/03/2021
by   Matthew Reimherr, et al.
0

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 Fréchet 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/25/2019

Riemannian optimization on the simplex of positive definite matrices

We discuss optimization-related ingredients for the Riemannian manifold ...
09/04/2020

Density estimation and modeling on symmetric spaces

In many applications, data and/or parameters are supported on non-Euclid...
05/02/2007

Riemannian level-set methods for tensor-valued data

We present a novel approach for the derivation of PDE modeling curvature...
12/30/2018

Geometrical and statistical properties of M-estimates of scatter on Grassmann manifolds

We consider data from the Grassmann manifold G(m,r) of all vector subspa...
05/14/2018

H-CNNs: Convolutional Neural Networks for Riemannian Homogeneous Spaces

Convolutional neural networks are ubiquitous in Machine Learning applica...
12/01/2017

Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection

Inter-subject variability between individuals poses a challenge in inter...
02/22/2021

Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval

Differential Privacy offers strong guarantees such as immutable privacy ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.