Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples

DOI10.1007/S11425-018-9554-4MaRDI QIDQ829393zbMATH OpenOpenAlexFDO

Authors Siyun Zhou, Yanqin Bai

Publication date 6 May 2021

Published in Science China. Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11425-018-9554-4

zbMATH Keywords

convergence ratenonzero-mean samplesOja's algorithmonline PCA (principal component analysis)

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Factor analysis and principal components; correspondence analysis (62H25) Stochastic approximation (62L20) Statistical aspects of big data and data science (62R07) Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Nonconvex programming, global optimization (90C26)

Recommendations

• On the optimality of the Oja's algorithm for online PCA
• Nearly optimal stochastic approximation for online principal subspace estimation
• Near-optimal stochastic approximation for online principal component estimation
• Stochastic Gauss-Newton algorithms for online PCA
• Online principal components analysis

Cites work

• A simplified neuron model as a principal component analyzer
• An introduction to matrix concentration inequalities
• Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate
• Low-rank incremental methods for computing dominant singular subspaces
• Method of stochastic approximation in the determination of the largest eigenvalue of the mathematical expectation of random matrices
• Near-optimal stochastic approximation for online principal component estimation
• On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
• Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?

Cited in

(9)

• Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods
• Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate
• Nearly optimal stochastic approximation for online principal subspace estimation
• The convergence properties of infeasible inexact proximal alternating linearized minimization
• Stochastic Gauss-Newton algorithms for online PCA
• On the optimality of the Oja's algorithm for online PCA
• Near-optimal stochastic approximation for online principal component estimation
• An orthonormalization-free and inversion-free algorithm for online estimation of principal eigenspace
• Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate

This page was built for publication: Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q829393)