A Framework for Private Matrix Analysis

09/06/2020
by   Jalaj Upadhyay, et al.
0

We study private matrix analysis in the sliding window model where only the last W updates to matrices are considered useful for analysis. We give first efficient o(W) space differentially private algorithms for spectral approximation, principal component analysis, and linear regression. We also initiate and show efficient differentially private algorithms for two important variants of principal component analysis: sparse principal component analysis and non-negative principal component analysis. Prior to our work, no such result was known for sparse and non-negative differentially private principal component analysis even in the static data setting. These algorithms are obtained by identifying sufficient conditions on positive semidefinite matrices formed from streamed matrices. We also show a lower bound on space required to compute low-rank approximation even if the algorithm gives multiplicative approximation and incurs additive error. This follows via reduction to a certain communication complexity problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/19/2015

Modularity Component Analysis versus Principal Component Analysis

In this paper the exact linear relation between the leading eigenvectors...
research
07/06/2022

Private Matrix Approximation and Geometry of Unitary Orbits

Consider the following optimization problem: Given n × n matrices A and ...
research
11/18/2015

Wishart Mechanism for Differentially Private Principal Components Analysis

We propose a new input perturbation mechanism for publishing a covarianc...
research
11/23/2022

Improved approximation and visualization of the correlation matrix

The graphical representation of the correlation matrix by means of diffe...
research
12/03/2020

Average-Case Integrality Gap for Non-Negative Principal Component Analysis

Montanari and Richard (2015) asked whether a natural semidefinite progra...
research
03/18/2022

Generative Principal Component Analysis

In this paper, we study the problem of principal component analysis with...
research
04/19/2011

High-Dimensional Inference with the generalized Hopfield Model: Principal Component Analysis and Corrections

We consider the problem of inferring the interactions between a set of N...

Please sign up or login with your details

Forgot password? Click here to reset