Optimally Weighted PCA for High-Dimensional Heteroscedastic Data

DOI10.1137/22M1470244MaRDI QIDQ5888296zbMATH OpenOpenAlexFDO

Authors

Publication date 24 April 2023

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.12862

zbMATH Keywords

heterogeneous qualitylarge-dimensional dataoptimal weightingprincipal component analysis

Mathematics Subject Classification ID

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

Recommendations

• Heteroskedastic PCA: algorithm, optimality, and applications
• Asymptotic performance of PCA for high-dimensional heteroscedastic data
• Inference for heteroskedastic PCA with missing data
• Sparse PCA: optimal rates and adaptive estimation

Cites work

• A necessary and sufficient condition for edge universality at the largest singular values of covariance matrices
• Anisotropic local laws for random matrices
• Asymptotic conditional singular value decomposition for high-dimensional genomic data
• Asymptotic performance of PCA for high-dimensional heteroscedastic data
• Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
• Bounds for a Mixture of Low-Rank Compound-Gaussian and White Gaussian Noises
• Clutter Subspace Estimation in Low Rank Heterogeneous Noise Context
• Convergence of eigenvector empirical spectral distribution of sample covariance matrices
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Finite sample approximation results for principal component analysis: A matrix perturbation approach
• HePPCAT: Probabilistic PCA for Data With Heteroscedastic Noise
• Heteroskedastic PCA: algorithm, optimality, and applications
• High-dimensional probability. An introduction with applications in data science
• Isotropic local laws for sample covariance and generalized Wigner matrices
• Low-Complexity Algorithms for Low Rank Clutter Parameters Estimation in Radar Systems
• Matrix denoising for weighted loss functions and heterogeneous signals
• Maximum likelihood estimation and factor analysis
• On consistency and sparsity for principal components analysis in high dimensions
• Optimal prediction in the linearly transformed spiked model
• Optimal shrinkage of eigenvalues in the spiked covariance model
• Optimal Spectral Shrinkage and PCA With Heteroscedastic Noise
• OptShrink: An Algorithm for Improved Low-Rank Signal Matrix Denoising by Optimal, Data-Driven Singular Value Shrinkage
• Principal component analysis.
• Robust Covariance Matrix Estimation in Heterogeneous Low Rank Context
• Statistical challenges of high-dimensional data
• The singular values and vectors of low rank perturbations of large rectangular random matrices
• Variational Analysis

Cited in

(5)

• Inference for heteroskedastic PCA with missing data
• Scalable magnetic resonance fingerprinting: incremental inference of high-dimensional elliptical mixtures from large data volumes
• The Dyson equalizer: adaptive noise stabilization for low-rank signal detection and recovery
• Deflated HeteroPCA: overcoming the curse of ill-conditioning in heteroskedastic PCA
• Certificate for orthogonal equivalence of real polynomials by polynomial-weighted principal component analysis

Describes a project that uses

Uses Software

• OptShrink

This page was built for publication: Optimally Weighted PCA for High-Dimensional Heteroscedastic Data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5888296)