Estimation of low-rank matrices via approximate message passing

DOI10.1214/20-AOS1958zbMath1461.62070arXiv1711.01682MaRDI QIDQ2656598

Yanyan Li

Publication date: 11 March 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.01682

zbMATH Keywords

approximate message passinglow-rank matrix estimationspectral initialization

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Asymptotic distribution theory in statistics (62E20) Bayesian inference (62F15) Random matrices (probabilistic aspects) (60B20) Inference from stochastic processes and spectral analysis (62M15)

Related Items (13)

Approximate message passing algorithms for rotationally invariant matrices ⋮ Approximate message passing with spectral initialization for generalized linear models* ⋮ Computational barriers to estimation from low-degree polynomials ⋮ Generalized TAP Free Energy ⋮ Fundamental limits of weak recovery with applications to phase retrieval ⋮ A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists ⋮ Universality of approximate message passing with semirandom matrices ⋮ Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization ⋮ On the TAP equations via the cavity approach in the generic mixed \(p\)-spin models ⋮ Universality of approximate message passing algorithms ⋮ On convergence of the cavity and Bolthausen's TAP iterations to the local magnetization ⋮ Optimal combination of linear and spectral estimators for generalized linear models ⋮ A Unifying Tutorial on Approximate Message Passing

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Sparse principal component analysis and iterative thresholding
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• The singular values and vectors of low rank perturbations of large rectangular random matrices
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Finding hidden cliques of size \(\sqrt{N/e}\) in nearly linear time
• The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations
• Spectral analysis of large dimensional random matrices
• Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
• Fundamental limits of symmetric low-rank matrix estimation
• Minimax estimation via wavelet shrinkage
• On the distribution of the largest eigenvalue in principal components analysis
• Universality in polytope phase transitions and message passing algorithms
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Eigenvalues of large sample covariance matrices of spiked population models
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• The Isotropic Semicircle Law and Deformation of Wigner Matrices
• Generalized power method for sparse principal component analysis
• Phase transitions in semidefinite relaxations
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
• Non-Negative Principal Component Analysis: Message Passing Algorithms and Sharp Asymptotics
• Accurate Prediction of Phase Transitions in Compressed Sensing via a Connection to Minimax Denoising
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• Community Detection and Stochastic Block Models
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences
• Asymptotic mutual information for the balanced binary stochastic block model
• A Direct Approach to False Discovery Rates
• Learning Theory
• The Computer Science and Physics of Community Detection: Landscapes, Phase Transitions, and Hardness
• State evolution for approximate message passing with non-separable functions
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• Iterative reconstruction of rank-one matrices in noise
• On Consistency and Sparsity for Principal Components Analysis in High Dimensions
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Learning the parts of objects by non-negative matrix factorization
• Optimal Transport

This page was built for publication: Estimation of low-rank matrices via approximate message passing