On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
From MaRDI portal
Publication:1069252
DOI10.1016/0022-247X(85)90131-3zbMath0583.62077WikidataQ31062593 ScholiaQ31062593MaRDI QIDQ1069252
Publication date: 1985
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
numerical resultseigenvectorsconvergence rateestimation errordominant eigenvaluesexpectation of a random matrixsimultaneous iteration method
Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Eigenvalues, singular values, and eigenvectors (15A18) Stochastic approximation (62L20) Random matrices (algebraic aspects) (15B52) Probabilistic methods, stochastic differential equations (65C99)
Related Items
Online sparse sliced inverse regression for high-dimensional streaming data, Streaming Principal Component Analysis From Incomplete Data, Influence of stochastic geometric imperfections on the load-carrying behaviour of thin-walled structures using constrained random fields, Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples, Hebbian errors in learning: an analysis using the Oja model, An adaptive constraint method for paraunitary filter banks with applications to spatiotemporal subspace tracking, Nonlinear differential equations in \({\mathcal{B}(\mathcal{H})}\) motivated by learning models, Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate, Convergence of solutions to equations arising in neural networks, Unnamed Item, Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control, The method of averaged models for discrete-time adaptive systems, Incremental modelling for compositional data streams, 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, On principal subspace analysis, Nearly optimal stochastic approximation for online principal subspace estimation, Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?, Past, current and future trends and challenges in non-deterministic fracture mechanics: a review, Stability behavior for unsupervised learning, Unnamed Item, On the optimality of the Oja's algorithm for online PCA, Convergence proof of matrix dynamics for online linear discriminant analysis, Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions, Input Statistics and Hebbian Cross-Talk Effects, A simplified neuron model as a principal component analyzer, A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data, Learning Visual Spatial Pooling by Strong PCA Dimension Reduction, A brief introduction to manifold optimization, Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods, Stability and chaos of LMSER PCA learning algorithm, Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate, Robust learning in a partial least-squares neural network, Global convergence of a PCA learning algorithm with a constant learning rate, Near-optimal stochastic approximation for online principal component estimation, Unsupervised streaming anomaly detection for instrumented infrastructure, Neural networks for computing eigenvalues and eigenvectors, Analyzing iterations in identification with application to nonparametric \(\mathcal H_{\infty}\)-norm estimation, Computational intelligence: From mathematical point of view, Neural networks based approach for computing eigenvectors and eigenvalues of symmetric matrix, Recursive estimation for ordered eigenvectors of symmetric matrix with observation noise, Global analysis of planar neural networks, Adaptive algorithms for first principal eigenvector computation, Differential equations in spaces of compact operators, Convergence rate of Krasulina estimator, Differential equations in Schatten classes of operators, A dual purpose principal and minor component flow, A note on linear function approximation using random projections, On the Organization of Grid and Place Cells: Neural Denoising via Subspace Learning, DESIGNING RELEVANT FEATURES FOR CONTINUOUS DATA SETS USING ICA, Hybrid uncertain natural frequency analysis for structures with random and interval fields, Analysis of a stochastic approximation algorithm for computing quasi-stationary distributions, AgFlow: fast model selection of penalized PCA via implicit regularization effects of gradient flow, Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams, Dual Randomized Coordinate Descent Method for Solving a Class of Nonconvex Problems, Object recognition using a neural network with optimal feature extraction., The scaling limit of high-dimensional online independent component analysis, Unnamed Item, A learning rule with generalized Hebbian synapses, Distributed user profiling via spectral methods, Neurodynamics and nonlinear integrable systems of Lax type
Cites Work
- Stochastic approximation methods for constrained and unconstrained systems
- An analysis of convergence for a learning version of the subspace method
- Computational aspects of F. L. Bauer's simultaneous iteration method
- 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.)
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
