On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix

DOI10.1016/0022-247X(85)90131-3zbMATH Open0583.62077WikidataQ31062593 ScholiaQ31062593MaRDI QIDQ1069252FDOQ1069252

Authors: Erkki Oja, Juha Karhunen 

Publication date: 1985

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Recommendations

• scientific article; zbMATH DE number 1275344
• scientific article; zbMATH DE number 1036075
• scientific article; zbMATH DE number 597683
• scientific article
• Adaptive algorithms for first principal eigenvector computation

zbMATH Keywords

numerical resultseigenvectorsconvergence rateestimation errordominant eigenvaluesexpectation of a random matrixsimultaneous iteration method

Mathematics Subject Classification ID

Probabilistic methods, stochastic differential equations (65C99) Eigenvalues, singular values, and eigenvectors (15A18) Random matrices (algebraic aspects) (15B52) Stochastic approximation (62L20) Numerical computation of eigenvalues and eigenvectors of matrices (65F15)

Cites Work

• Title not available (Why is that?)
• Stochastic approximation methods for constrained and unconstrained systems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Method of stochastic approximation in the determination of the largest eigenvalue of the mathematical expectation of random matrices
• On the generalized Karhunen-Loeve expansion (Corresp.)
• Computational aspects of F. L. Bauer's simultaneous iteration method
• An analysis of convergence for a learning version of the subspace method

Cited In (71)

• Approximation of some moments in eigenvalue problem including some random variables and its application
• On principal subspace analysis
• Past, current and future trends and challenges in non-deterministic fracture mechanics: a review
• Neural networks for computing eigenvalues and eigenvectors
• Title not available (Why is that?)
• Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples
• Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?
• Title not available (Why is that?)
• Differential equations in Schatten classes of operators
• Title not available (Why is that?)
• Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods
• Analyzing iterations in identification with application to nonparametric \(\mathcal H_{\infty}\)-norm estimation
• Computational intelligence: From mathematical point of view
• An adaptive constraint method for paraunitary filter banks with applications to spatiotemporal subspace tracking
• Global analysis of planar neural networks
• Eigenmeasures and stochastic diagonalization of bilinear maps
• Nonlinear differential equations in \({\mathcal{B}(\mathcal{H})}\) motivated by learning models
• Recursive estimation for ordered eigenvectors of symmetric matrix with observation noise
• Adaptive algorithms for first principal eigenvector computation
• Hebbian errors in learning: an analysis using the Oja model
• Majorization, doubly stochastic matrices, and comparison of eigenvalues
• Title not available (Why is that?)
• Incremental slow feature analysis: adaptive low-complexity slow feature updating from high-dimensional input streams
• Influence of stochastic geometric imperfections on the load-carrying behaviour of thin-walled structures using constrained random fields
• Title not available (Why is that?)
• Neural networks based approach for computing eigenvectors and eigenvalues of symmetric matrix
• Differential equations in spaces of compact operators
• Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate
• Stability and chaos of LMSER PCA learning algorithm
• Global convergence of a PCA learning algorithm with a constant learning rate
• Unsupervised streaming anomaly detection for instrumented infrastructure
• Hybrid uncertain natural frequency analysis for structures with random and interval fields
• Dual Randomized Coordinate Descent Method for Solving a Class of Nonconvex Problems
• A brief introduction to manifold optimization
• Object recognition using a neural network with optimal feature extraction.
• Analysis of a stochastic approximation algorithm for computing quasi-stationary distributions
• Neurodynamics and nonlinear integrable systems of Lax type
• Adaptive multiple minor directions extraction in parallel using a PCA neural network
• Another neural network based approach for computing eigenvalues and eigenvectors of real skew-symmetric matrices
• Distributed user profiling via spectral methods
• On stochastic majorization of the eigenvalues of a Wishart matrix
• A dual purpose principal and minor component flow
• A note on linear function approximation using random projections
• A learning rule with generalized Hebbian synapses
• Convergence rate of Krasulina estimator
• A simplified neuron model as a principal component analyzer
• Convergence proof of matrix dynamics for online linear discriminant analysis
• Nearly optimal stochastic approximation for online principal subspace estimation
• Streaming Principal Component Analysis From Incomplete Data
• The method of averaged models for discrete-time adaptive systems
• Stability behavior for unsupervised learning
• Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control
• Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate
• AgFlow: fast model selection of penalized PCA via implicit regularization effects of gradient flow
• Robust learning in a partial least-squares neural network
• Some Approximation Formula for Stochastic Eigenvalues
• Convergence of solutions to equations arising in neural networks
• Title not available (Why is that?)
• A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
• Near-optimal stochastic approximation for online principal component estimation
• Incremental modelling for compositional data streams
• DESIGNING RELEVANT FEATURES FOR CONTINUOUS DATA SETS USING ICA
• Online sparse sliced inverse regression for high-dimensional streaming data
• Title not available (Why is that?)
• The scaling limit of high-dimensional online independent component analysis
• On the optimality of the Oja's algorithm for online PCA
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data
• Input Statistics and Hebbian Cross-Talk Effects
• Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions
• On the Organization of Grid and Place Cells: Neural Denoising via Subspace Learning
• Learning Visual Spatial Pooling by Strong PCA Dimension Reduction

This page was built for publication: On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1069252)