Principal Component Analysis in the local differential privacy model

被引:14
|
作者
Wang, Di [1 ]
Xu, Jinhui [1 ]
机构
[1] SUNY Buffalo, Dept Comp Sci & Engn, 338 Davis Hall, Buffalo, NY 14260 USA
关键词
Local differential privacy; Principal Component Analysis; Sparse PCA;
D O I
10.1016/j.tcs.2019.12.019
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, we study the Principal Component Analysis (PCA) problem under the (distributed) non-interactive local differential privacy model. For the low dimensional case (i.e., p << n), we show the optimal rate of Theta(kp/n epsilon(2)) (omitting the eigenvalue terms) for the private minimax risk of the k-dimensional PCA using the squared subspace distance as the measurement, where n is the sample size and E is the privacy parameter. For the high dimensional (i.e., p >> n) row sparse case, we first give a lower bound of Omega(ks log p/n epsilon(2))) on the private minimax risk, where s is the underlying sparsity parameter. Then we provide an efficient algorithm to achieve the upper bound of O(s(2) log p/n epsilon(2)). Experiments on both synthetic and real world datasets confirm our theoretical guarantees. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码:296 / 312
页数:17
相关论文
共 50 条
  • [21] Differential principal component analysis of ChIP-seq
    Ji, Hongkai
    Li, Xia
    Wang, Qian-fei
    Ning, Yang
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2013, 110 (17) : 6789 - 6794
  • [22] Local and global principal component analysis for process monitoring
    Yu, Jianbo
    JOURNAL OF PROCESS CONTROL, 2012, 22 (07) : 1358 - 1373
  • [23] Adaptive Dimensionality Reduction for Local Principal Component Analysis
    Migenda, Nico
    Schenck, Wolfram
    2020 25TH IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA), 2020, : 1575 - 1582
  • [24] Local independent component analysis with fuzzy clustering and regression-principal component analysis
    Maenaka, Tatsuya
    Honda, Katsuhiro
    Ichihashi, Hidetomo
    2006 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-5, 2006, : 857 - +
  • [25] On Facility Location Problem in the Local Differential Privacy Model
    Cohen-Addad, Vincent
    Esencayi, Yunus
    Fan, Chenglin
    Gaboradi, Marco
    Li, Shi
    Wang, Di
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [26] On Sparse Linear Regression in the Local Differential Privacy Model
    Wang, Di
    Xu, Jinhui
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (02) : 1182 - 1200
  • [27] On Sparse Linear Regression in the Local Differential Privacy Model
    Wang, Di
    Xu, Jinhui
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [28] COMMON FACTOR-ANALYSIS VERSUS PRINCIPAL COMPONENT ANALYSIS - DIFFERENTIAL BIAS IN REPRESENTING MODEL PARAMETERS
    WIDAMAN, KF
    MULTIVARIATE BEHAVIORAL RESEARCH, 1993, 28 (03) : 263 - 311
  • [29] The use of principal component analysis and discriminant analysis in differential sensing routines
    Stewart, Sara
    Ivy, Michelle Adams
    Anslyn, Eric V.
    CHEMICAL SOCIETY REVIEWS, 2014, 43 (01) : 70 - 84
  • [30] Mobile Data Collection and Analysis with Local Differential Privacy
    Li, Ninghui
    Ye, Qingqing
    2019 20TH INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2019), 2019, : 4 - 7