Smooth sensitivity based approach for differentially private principal component analysis

MaRDI QIDQ4617616zbMATH OpenFDO

Authors Alon Gonen, Ran Gilad-Bachrach

Publication date 6 February 2019

Full work available at URL https://arxiv.org/abs/1710.10556, http://proceedings.mlr.press/v83/gonem18a/gonem18a.pdf

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Data encryption (aspects in computer science) (68P25)

Recommendations

• A near-optimal algorithm for differentially-private principal components
• Principal component analysis in the local differential privacy model
• Analyze Gauss: optimal bounds for privacy-preserving principal component analysis
• On differentially private low rank approximation
• Differentially private high dimensional sparse covariance matrix estimation

Cited in

(8)

• Beyond worst-case analysis in private singular vector computation
• Differential privacy data publishing method based on the probabilistic principal component analysis
• Private low-rank approximation for covariance matrices, Dyson Brownian motion, and eigenvalue-gap bounds for Gaussian perturbations
• A near-optimal algorithm for differentially-private principal components
• SENSITIVITY-INDEPENDENT DIFFERENTIAL PRIVACY VIA PRIOR KNOWLEDGE REFINEMENT
• Analyze Gauss: optimal bounds for privacy-preserving principal component analysis
• Principal component analysis in the local differential privacy model
• Infinite-dimensional stochastic transforms and reproducing kernel Hilbert space

This page was built for publication: Smooth sensitivity based approach for differentially private principal component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4617616)