Timezone: »
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 Fr\'echet 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.
Author Information
Matthew Reimherr (Penn State University)
Karthik Bharath (University of Nottingham)
Carlos Soto (Pennsylvania State University)
More from the Same Authors
-
2022 Poster: Shape And Structure Preserving Differential Privacy »
Carlos Soto · Karthik Bharath · Matthew Reimherr · Aleksandra Slavković -
2021 Poster: Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms »
Jeremy Seeman · Matthew Reimherr · Aleksandra Slavković -
2021 Poster: A Highly-Efficient Group Elastic Net Algorithm with an Application to Function-On-Scalar Regression »
Tobia Boschi · Matthew Reimherr · Francesca Chiaromonte -
2019 Poster: Invariance and identifiability issues for word embeddings »
Rachel Carrington · Karthik Bharath · Simon Preston