DeepAI AI Chat
Log In Sign Up

Wishart Mechanism for Differentially Private Principal Components Analysis

by   Wuxuan Jiang, et al.
Shanghai Jiao Tong University

We propose a new input perturbation mechanism for publishing a covariance matrix to achieve (ϵ,0)-differential privacy. Our mechanism uses a Wishart distribution to generate matrix noise. In particular, We apply this mechanism to principal component analysis. Our mechanism is able to keep the positive semi-definiteness of the published covariance matrix. Thus, our approach gives rise to a general publishing framework for input perturbation of a symmetric positive semidefinite matrix. Moreover, compared with the classic Laplace mechanism, our method has better utility guarantee. To the best of our knowledge, Wishart mechanism is the best input perturbation approach for (ϵ,0)-differentially private PCA. We also compare our work with previous exponential mechanism algorithms in the literature and provide near optimal bound while having more flexibility and less computational intractability.


page 1

page 2

page 3

page 4


Differentially private low-dimensional representation of high-dimensional data

Differentially private synthetic data provide a powerful mechanism to en...

A Framework for Private Matrix Analysis

We study private matrix analysis in the sliding window model where only ...

Near-Optimal Algorithms for Differentially-Private Principal Components

Principal components analysis (PCA) is a standard tool for identifying g...

Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion

Given a symmetric matrix M and a vector λ, we present new bounds on the ...

Differentially Private High Dimensional Sparse Covariance Matrix Estimation

In this paper, we study the problem of estimating the covariance matrix ...

Distributed Differentially-Private Algorithms for Matrix and Tensor Factorization

In many signal processing and machine learning applications, datasets co...

Covariance loss, Szemeredi regularity, and differential privacy

We show how randomized rounding based on Grothendieck's identity can be ...