Minimax-optimal privacy-preserving sparse PCA in distributed systems

Jason Ge, Zhaoran Wang, Mengdi Wang, Han Liu

Research output: Contribution to conferencePaperpeer-review

30 Scopus citations


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.

Original languageEnglish (US)
Number of pages10
StatePublished - Jan 1 2018
Event21st International Conference on Artificial Intelligence and Statistics, AISTATS 2018 - Playa Blanca, Lanzarote, Canary Islands, Spain
Duration: Apr 9 2018Apr 11 2018


Conference21st International Conference on Artificial Intelligence and Statistics, AISTATS 2018
CityPlaya Blanca, Lanzarote, Canary Islands

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Artificial Intelligence


Dive into the research topics of 'Minimax-optimal privacy-preserving sparse PCA in distributed systems'. Together they form a unique fingerprint.

Cite this