The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf
.
Near-Optimal Algorithms for Differentially-Private Principal Components
[article]
2013
arXiv
pre-print
Principal components analysis (PCA) is a standard tool for identifying good low-dimensional approximations to data in high dimension. Many data sets of interest contain private or sensitive information about individuals. Algorithms which operate on such data should be sensitive to the privacy risks in publishing their outputs. Differential privacy is a framework for developing tradeoffs between privacy and the utility of these outputs. In this paper we investigate the theory and empirical
arXiv:1207.2812v3
fatcat:y26kyvki45auzh7ku346prfrhi