cs.DScs.LG

Gap-free Differentially Private PCA for Gaussian Data

📅 👥 2 authors arXiv:2609.31614v2

Authors

Abstract

We give a gap-free $(ε,δ)$-differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data. The algorithm is based on a private variant of the power iteration method, and it is computationally efficient.

Paper Information

arXiv ID:
2609.31614v2
Published:

Related Categories

cs.DScs.LG