AI RESEARCH
Adaptive Power Iteration Method for Differentially Private PCA
arXiv CS.LG
•
ArXi:2602.11454v3 Announce Type: replace-cross We study $\left(\epsilon,\delta\right)$-differentially private algorithms for the problem of approximately computing the top singular vector of a matrix $A\in\mathbb{R}^{n\times d}$ where each row of $A$ is a data point in $\mathbb{R}^{d}$. Following Dwork-Talwar-Thakurta-Zhang (STOC 2014), we consider the privacy model where neighboring inputs differ by one single row.