cs.DSFeb 12, 2026

Adaptive Power Iteration Method for Differentially Private PCA

Authors: Ta Duy Nguyen, Alina Ene, Huy Le Nguyen

Organizations: Department of Computer Science, Boston University · Khoury College of Computer and Information Science, Northeastern University

Abstract

We study (ε,δ)\left(ε,δ\right)-differentially private algorithms for the problem of approximately computing the top singular vector of a matrix A∈Rn×dA\in\mathbb{R}^{n\times d} where each row of AA is a data point in Rd\mathbb{R}^{d}. Following Dwork-Talwar-Thakurta-Zhang (STOC 2014), we consider the privacy model where neighboring inputs differ by one single row. We give a novel algorithm that achieves beyond-worst-case guarantees for input matrices with low coherence, which is a structural property of matrices in many applications, including but not limited to i.i.d. data. Our algorithm contributes to the extensive literature on private power iteration methods, where we introduce a new filtering technique which adapts to this coherence parameter. Our work departs from and complements the work by Hardt-Roth (STOC 2013) which achieves beyond-worst-case guarantees for the more restrictive privacy model where neighboring inputs differ in one single entry by at most 1.

Figures & tables

Explore similar work

CardsList
  1. Gap-free Differentially Private PCA for Gaussian Data

    Sep 25, 2026Alina Ene, Huy L. NguyenPrincipal Component AnalysisDifferential Privacy

  2. Optimal Rates for Adaptive Private kk-PCA

    Nov 9, 2026Johanna Düngler, Amartya SanyalPrincipal Component AnalysisDifferential Privacy

  3. On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCA

    Jun 20, 2026Syamantak Kumar, Shourya Pandey, Purnamrita Sarkar +1Principal Component AnalysisMinimax Estimation