Skip to main content

Minimax-optimal privacy-preserving sparse PCA in distributed systems

Author(s): Ge, Jason; Wang, Zhaoran; Wang, Mengdi; Liu, Han

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1hj36
Abstract: Copyright 2018 by the author(s). This paper proposes a distributed privacy-preserving sparse PCA (DPS-PCA) algorithm that generates a minimax-optimal sparse PCA estimator under differential privacy constraints. In a distributed optimization framework, data providers can use this algorithm to collaboratively analyze the union of their data sets while limiting the disclosure of their private information. DPS-PCA can recover the leading eigenspace of the population covariance at a geometric convergence rate, and simultaneously achieves the optimal minimax statistical error for high-dimensional data. Our algorithm provides fine-tuned control over the tradeoff between estimation accuracy and privacy preservation. Numerical simulations demonstrate that DPS-PCA significantly outperforms other privacy-preserving PCA methods in terms of estimation accuracy and computational efficiency.
Publication Date: 1-Jan-2018
Citation: Ge, J, Wang, Z, Wang, M, Liu, H. (2018). Minimax-optimal privacy-preserving sparse PCA in distributed systems. International Conference on Artificial Intelligence and Statistics, AISTATS 2018, 1589 - 1598
Pages: 1589 - 1598
Type of Material: Journal Article
Journal/Proceeding Title: International Conference on Artificial Intelligence and Statistics, AISTATS 2018
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.