Sparse principal component analysis and iterative thresholding
From MaRDI portal
Abstract: Principal component analysis (PCA) is a classical dimension reduction method which projects data onto the principal subspace spanned by the leading eigenvectors of the covariance matrix. However, it behaves poorly when the number of features p is comparable to, or even much larger than, the sample size n. In this paper, we propose a new iterative thresholding approach for estimating principal subspaces in the setting where the leading eigenvectors are sparse. Under a spiked covariance model, we find that the new approach recovers the principal subspace and leading eigenvectors consistently, and even optimally, in a range of high-dimensional sparse settings. Simulated examples also demonstrate its competitive performance.
Recommendations
Cites work
- scientific article; zbMATH DE number 47363 (Why is no real title available?)
- scientific article; zbMATH DE number 961607 (Why is no real title available?)
- A Direct Formulation for Sparse PCA Using Semidefinite Programming
- A Gaussian scenario for unsupervised learning
- A wavelet tour of signal processing. The sparse way.
- Analysis of Financial Time Series
- Asymptotic Theory for Principal Component Analysis
- Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
- Asymptotics of the principal components estimator of large factor models with weakly influential factors
- Consistency of sparse PCA in high dimension, low sample size contexts
- Discussion
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- Functional data analysis.
- High-dimensional analysis of semidefinite relaxations for sparse principal components
- Learning Theory
- On consistency and sparsity for principal components analysis in high dimensions
- On the distribution of the largest eigenvalue in principal components analysis
- PCA consistency in high dimension, low sample size context
- Perturbation bounds in connection with singular value decomposition
- Sparse Variable PCA Using Geodesic Steepest Descent
- Sparse principal component analysis and iterative thresholding
- Sparse principal component analysis via regularized low rank matrix approximation
- The Rotation of Eigenvectors by a Perturbation. III
- Truncated power method for sparse eigenvalue problems
- Unconditional bases are optimal bases for data compression and for statistical estimation
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(only showing first 100 items - show all)- Hypothesis tests for large density matrices of quantum systems based on Pauli measurements
- Overlapping community detection in networks via sparse spectral decomposition
- Testing and estimating change-points in the covariance matrix of a high-dimensional time series
- Sparse PCA-based on high-dimensional Itô processes with measurement errors
- An empirical comparison of two approaches for CDPCA in high-dimensional data
- Projected principal component analysis in factor models
- Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
- Recent developments in high dimensional covariance estimation and its related issues, a review
- Minimax bounds for sparse PCA with noisy high-dimensional data
- Sparse PCA: optimal rates and adaptive estimation
- Sparse power factorization: balancing peakiness and sample complexity
- A tight bound of hard thresholding
- Do semidefinite relaxations solve sparse PCA up to the information limit?
- An \(\ell_{\infty}\) eigenvector perturbation bound and its application
- Scale-invariant sparse PCA on high-dimensional meta-elliptical data
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- On consistency and sparsity for principal components analysis in high dimensions
- Principal component analysis in very high-dimensional spaces
- Large covariance estimation through elliptical factor models
- Sparse PCA by iterative elimination algorithm
- Sparse principal component analysis in Hilbert space
- New asymptotic results in principal component analysis
- Simple Poisson PCA: an algorithm for (sparse) feature extraction with simultaneous dimension determination
- High-resolution signal recovery via generalized sampling and functional principal component analysis
- Estimation of low-rank matrices via approximate message passing
- The spectral norm of random inner-product kernel matrices
- Optimal sparse eigenspace and low-rank density matrix estimation for quantum systems
- Sparse principal component analysis with missing observations
- Near-optimal stochastic approximation for online principal component estimation
- Sparse PCA via covariance thresholding
- Optimal detection of sparse principal components in high dimension
- Modified Mahalanobis-Taguchi system based on proper orthogonal decomposition for high-dimensional-small-sample-size data classification
- Convergence of eigenvector empirical spectral distribution of sample covariance matrices
- Principal component analysis of binary data by iterated singular value decomposition
- Sparse principal component analysis for high‐dimensional stationary time series
- scientific article; zbMATH DE number 7370563 (Why is no real title available?)
- Large dimensional analysis of general margin based classification methods
- Testing equivalence of clustering
- Optimal estimation and rank detection for sparse spiked covariance matrices
- An augmented Lagrangian approach for sparse principal component analysis
- The benefit of group sparsity in group inference with de-biased scaled group Lasso
- An Iterative Bayesian Algorithm for Sparse Component Analysis in Presence of Noise
- Sparse principal component analysis with missing observations
- Penalized Orthogonal Iteration for Sparse Estimation of Generalized Eigenvalue Problem
- Bernstein-von Mises theorems for functionals of the covariance matrix
- Convergence rates of eigenvector empirical spectral distribution of large dimensional sample covariance matrix
- Sparse principal component analysis by choice of norm
- Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
- Likelihood ratio test in multivariate linear regression: from low to high dimension
- Sparse generalized principal component analysis for large-scale applications beyond Gaussianity
- Universal latent space model fitting for large networks with edge covariates
- Minimax estimation in sparse canonical correlation analysis
- Minimax sparse principal subspace estimation in high dimensions
- Robust covariance estimation for approximate factor models
- Robust covariance and scatter matrix estimation under Huber's contamination model
- Statistical inference for principal components of spiked covariance matrices
- Projection sparse principal component analysis: an efficient least squares method
- Optimality and sub-optimality of PCA. I: Spiked random matrix models
- Sparsistency and agnostic inference in sparse PCA
- Random matrix theory in statistics: a review
- Certifiably optimal sparse principal component analysis
- Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
- Convergence rate of eigenvector empirical spectral distribution of large Wigner matrices
- ECA: High-Dimensional Elliptical Component Analysis in Non-Gaussian Distributions
- Integrative sparse principal component analysis
- Rate-optimal posterior contraction for sparse PCA
- Sparse principal component analysis and iterative thresholding
- Estimation of functionals of sparse covariance matrices
- scientific article; zbMATH DE number 7415123 (Why is no real title available?)
- Sequential Scaled Sparse Factor Regression
- Eigenvectors from Eigenvalues Sparse Principal Component Analysis
- Fundamental limits of low-rank matrix estimation with diverging aspect ratios
- Scalable interpretable multi-response regression via SEED
- Dynamic Principal Component Analysis in High Dimensions
- Sparse Principal Component Analysis Based on Least Trimmed Squares
- Euclidean Representation of Low-Rank Matrices and Its Geometric Properties
- Trace Ratio Optimization for High-Dimensional Multi-Class Discrimination
- Envelopes and principal component regression
- Fast deflation sparse principal component analysis via subspace projections
- Smoothing algorithms for nonsmooth optimization over the Stiefel manifold with applications to the graph Fourier basis problem
- Linear spectral statistics of eigenvectors of anisotropic sample covariance matrices
- Large volatility matrix analysis using global and national factor models
- An efficient algorithm for Fantope-constrained sparse principal subspace estimation problem
- Long random matrices and tensor unfolding
- Compressed covariance estimation with automated dimension learning
- Large scale analysis of generalization error in learning using margin based classification methods
- On Cross-Validation for Sparse Reduced Rank Regression
- A data-driven approach to conditional screening of high-dimensional variables
- Tensor canonical correlation analysis
- Sparse principal component analysis based on transformed \({L_1}\) penalty
- Partially Observed Dynamic Tensor Response Regression
- Provable sample-efficient sparse phase retrieval initialized by truncated power method
- Integrative Factor Regression and Its Inference for Multimodal Data Analysis
- Recovering PCA and sparse PCA via hybrid-\((\ell_1,\ell_2)\) sparse sampling of data elements
- Sparse constrained projection approximation subspace tracking
- A penalty-free infeasible approach for a class of nonsmooth optimization problems over the Stiefel manifold
- Smoothing composite proximal gradient algorithm for sparse group Lasso problems with nonsmooth loss functions
- Automatic sparse principal component analysis
- Sparse equisigned PCA: algorithms and performance bounds in the noisy rank-1 setting
- A fast, provably accurate approximation algorithm for sparse principal component analysis reveals human genetic variation across the world
This page was built for publication: Sparse principal component analysis and iterative thresholding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q355104)
