跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2602.11454 · v4

Adaptive Power Iteration Method for Differentially Private PCA

首次提交 2026-02-12 08:07
版本更新 2026-11-13 12:24
雷达观测 2026-11-17 04:57
arXiv ↗PDF ↗

摘要

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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v4,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v4 · 2026-11-13 12:24 · 最新观测版本

Adaptive Power Iteration Method for Differentially Private PCA

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.

查看此版本解读 →查看此版本原文 ↗