An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Düngler, Johanna, Sanyal, Amartya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916899647913984
author Düngler, Johanna
Sanyal, Amartya
author_facet Düngler, Johanna
Sanyal, Amartya
contents Given $n$ i.i.d. random matrices $A_i \in \mathbb{R}^{d \times d}$ that share a common expectation $Σ$, the objective of Differentially Private Stochastic PCA is to identify a subspace of dimension $k$ that captures the largest variance directions of $Σ$, while preserving differential privacy (DP) of each individual $A_i$. Existing methods either (i) require the sample size $n$ to scale super-linearly with dimension $d$, even under Gaussian assumptions on the $A_i$, or (ii) introduce excessive noise for DP even when the intrinsic randomness within $A_i$ is small. Liu et al. (2022a) addressed these issues for sub-Gaussian data but only for estimating the top eigenvector ($k=1$) using their algorithm DP-PCA. We propose the first algorithm capable of estimating the top $k$ eigenvectors for arbitrary $k \leq d$, whilst overcoming both limitations above. For $k=1$ our algorithm matches the utility guarantees of DP-PCA, achieving near-optimal statistical error even when $n = \tilde{\!O}(d)$. We further provide a lower bound for general $k > 1$, matching our upper bound up to a factor of $k$, and experimentally demonstrate the advantages of our algorithm over comparable baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
Düngler, Johanna
Sanyal, Amartya
Machine Learning
Cryptography and Security
Information Theory
Statistics Theory
Given $n$ i.i.d. random matrices $A_i \in \mathbb{R}^{d \times d}$ that share a common expectation $Σ$, the objective of Differentially Private Stochastic PCA is to identify a subspace of dimension $k$ that captures the largest variance directions of $Σ$, while preserving differential privacy (DP) of each individual $A_i$. Existing methods either (i) require the sample size $n$ to scale super-linearly with dimension $d$, even under Gaussian assumptions on the $A_i$, or (ii) introduce excessive noise for DP even when the intrinsic randomness within $A_i$ is small. Liu et al. (2022a) addressed these issues for sub-Gaussian data but only for estimating the top eigenvector ($k=1$) using their algorithm DP-PCA. We propose the first algorithm capable of estimating the top $k$ eigenvectors for arbitrary $k \leq d$, whilst overcoming both limitations above. For $k=1$ our algorithm matches the utility guarantees of DP-PCA, achieving near-optimal statistical error even when $n = \tilde{\!O}(d)$. We further provide a lower bound for general $k > 1$, matching our upper bound up to a factor of $k$, and experimentally demonstrate the advantages of our algorithm over comparable baselines.
title An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
topic Machine Learning
Cryptography and Security
Information Theory
Statistics Theory
url https://arxiv.org/abs/2508.10879