Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, T. Tony, Xia, Dong, Zha, Mengyue
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909327747448832
author Cai, T. Tony
Xia, Dong
Zha, Mengyue
author_facet Cai, T. Tony
Xia, Dong
Zha, Mengyue
contents Estimating a covariance matrix and its associated principal components is a fundamental problem in contemporary statistics. While optimal estimation procedures have been developed with well-understood properties, the increasing demand for privacy preservation introduces new complexities to this classical problem. In this paper, we study optimal differentially private Principal Component Analysis (PCA) and covariance estimation within the spiked covariance model. We precisely characterize the sensitivity of eigenvalues and eigenvectors under this model and establish the minimax rates of convergence for estimating both the principal components and covariance matrix. These rates hold up to logarithmic factors and encompass general Schatten norms, including spectral norm, Frobenius norm, and nuclear norm as special cases. We propose computationally efficient differentially private estimators and prove their minimax optimality for sub-Gaussian distributions, up to logarithmic factors. Additionally, matching minimax lower bounds are established. Notably, compared to the existing literature, our results accommodate a diverging rank, a broader range of signal strengths, and remain valid even when the sample size is much smaller than the dimension, provided the signal strength is sufficiently strong. Both simulation studies and real data experiments demonstrate the merits of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03820
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices
Cai, T. Tony
Xia, Dong
Zha, Mengyue
Statistics Theory
Information Theory
Methodology
Machine Learning
Estimating a covariance matrix and its associated principal components is a fundamental problem in contemporary statistics. While optimal estimation procedures have been developed with well-understood properties, the increasing demand for privacy preservation introduces new complexities to this classical problem. In this paper, we study optimal differentially private Principal Component Analysis (PCA) and covariance estimation within the spiked covariance model. We precisely characterize the sensitivity of eigenvalues and eigenvectors under this model and establish the minimax rates of convergence for estimating both the principal components and covariance matrix. These rates hold up to logarithmic factors and encompass general Schatten norms, including spectral norm, Frobenius norm, and nuclear norm as special cases. We propose computationally efficient differentially private estimators and prove their minimax optimality for sub-Gaussian distributions, up to logarithmic factors. Additionally, matching minimax lower bounds are established. Notably, compared to the existing literature, our results accommodate a diverging rank, a broader range of signal strengths, and remain valid even when the sample size is much smaller than the dimension, provided the signal strength is sufficiently strong. Both simulation studies and real data experiments demonstrate the merits of our method.
title Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices
topic Statistics Theory
Information Theory
Methodology
Machine Learning
url https://arxiv.org/abs/2401.03820