A near-optimal algorithm for differentially-private principal components

MaRDI QIDQ2933922zbMATH OpenFDO

Authors Kamalika Chaudhuri, Anand Dilip Sarwate, Kaushik Sinha

Publication date 8 December 2014

Full work available at URL https://arxiv.org/abs/1207.2812, http://jmlr.csail.mit.edu/papers/v14/chaudhuri13a.html

zbMATH Keywords

dimension reductionprincipal components analysisdifferential privacy

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25)

Recommendations

• Smooth sensitivity based approach for differentially private principal component analysis
• 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
• The algorithmic foundations of differential privacy

Cited in

(22)

• Tracy-Widom law for the extreme eigenvalues of large signal-plus-noise matrices
• Beyond worst-case analysis in private singular vector computation
• Differential privacy data publishing method based on the probabilistic principal component analysis
• PAC privacy: automatic privacy measurement and control of data processing
• Differentially private nearest neighbor classification
• Structure and sensitivity in differential privacy: comparing \(K\)-norm mechanisms
• A communication-efficient and privacy-aware distributed algorithm for sparse PCA
• On differentially private low rank approximation
• Segmentation, incentives, and privacy
• scientific article; zbMATH DE number 6860834 (Why is no real title available?)
• Comparative study of differentially private data synthesis methods
• Differentially-private learning of low dimensional manifolds
• Analyze Gauss: optimal bounds for privacy-preserving principal component analysis
• Mitigating the curse of dimensionality in data anonymization
• On the power of multiple anonymous messages: frequency estimation and selection in the shuffle model of differential privacy
• Smooth sensitivity based approach for differentially private principal component analysis
• Approximating Eigenvectors with Fixed-Point Arithmetic: A Step Towards Secure Spectral Clustering
• Differentially-private learning of low dimensional manifolds
• Principal component analysis in the local differential privacy model
• Bounded privacy-utility monotonicity indicating bounded tradeoff of differential privacy mechanisms
• A balm: defend the clique-based attack from a fundamental aspect
• New concepts of principal component analysis based on maximum separation of clusters

This page was built for publication: A near-optimal algorithm for differentially-private principal components

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2933922)