Recovering PCA from Hybrid-$(\ell_1,\ell_2)$ Sparse Sampling of Data Elements

zbMath1440.62044arXiv1503.00547MaRDI QIDQ4636984

Abhisek Kundu, Malik Magdon-Ismail, Petros Drineas

Publication date: 17 April 2018

Full work available at URL: https://arxiv.org/abs/1503.00547

zbMATH Keywords

sparse representationprincipal component analysis (PCA)sparse PCAelement-wise sampling

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Sampling theory, sample surveys (62D05) Missing data (62D10)

Related Items (1)

Comparison of matrix norm sparsification

Uses Software

• SpaSM

Cites Work

• Unnamed Item
• CUR matrix decompositions for improved data analysis
• Sparse principal component analysis and iterative thresholding
• Sparse principal component analysis via regularized low rank matrix approximation
• A note on element-wise matrix sparsification via a matrix-valued Bernstein inequality
• Sparsistency and agnostic inference in sparse PCA
• NP-hardness and inapproximability of sparse PCA
• Sparse PCA: optimal rates and adaptive estimation
• A note on sparse least-squares regression
• Sparse Principal Component Analysis with Missing Observations
• Fast computation of low-rank matrix approximations
• A Fast Random Sampling Algorithm for Sparsifying Matrices
• Fast computation of low rank matrix approximations
• A Simpler Approach to Matrix Completion
• Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication
• A Direct Formulation for Sparse PCA Using Semidefinite Programming

This page was built for publication: Recovering PCA from Hybrid-$(\ell_1,\ell_2)$ Sparse Sampling of Data Elements