Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

DOI10.1088/1742-5468/AC7E4COpenAlexW3206621305WikidataQ114096179 ScholiaQ114096179MaRDI QIDQ5101092FDOQ5101092

Authors: Antoine Maillard, Florent Krzakala, Marc Mézard, Lenka Zdeborová 

Publication date: 2 September 2022

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.08775

Recommendations

• Variational Methods for Denoising Matrix Fields
• Matrix factorizations and their perturbations
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Matrix spectral factorization with perturbed data
• Perturbation of matrices and nonnegative rank with a view toward statistical models
• Robust Low-Rank Matrix Factorization Under General Mixture Noise Distributions
• Reconstruction of a low-rank matrix in the presence of Gaussian noise
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Perturbation analysis of low-rank matrix stable recovery
• Constructive regularization of the random matrix norm

zbMATH Keywords

learning theorystatistical inferencespin glassesrandom matrix theory and extensions

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites Work

• Robust principal component analysis?
• Exact matrix completion via convex optimization
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Title not available (Why is that?)
• Complexity of random smooth functions on compact manifolds
• An introduction to random matrices
• Title not available (Why is that?)
• Addition of certain non-commuting random variables
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Title not available (Why is that?)
• The planar approximation. II
• Large deviations asymptotics for spherical integrals
• Differential Operators on a Semisimple Lie Algebra
• Optimal shrinkage of eigenvalues in the spiked covariance model
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• Information, Physics, and Computation
• Dictionary Learning Algorithms for Sparse Representation
• Universality in polytope phase transitions and message passing algorithms
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• Statistical Physics of Spin Glasses and Information Processing
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• Expectation consistent approximate inference
• Title not available (Why is that?)
• Large deviations and stochastic calculus for large random matrices
• Rectangular \(R\)-transform as the limit of rectangular spherical integrals
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• First order asymptotics of matrix integrals; a rigorous approach towards the understanding of matrix models
• On the large-\(N\) limit of the Itzykson-Zuber integral.
• Rotational Invariant Estimator for General Noisy Matrices
• Cleaning large correlation matrices: tools from random matrix theory
• Introduction to random matrices. Theory and practice
• Hydrodynamical spectral evolution for random matrices
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• Bilinear Generalized Approximate Message Passing—Part II: Applications
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
• A theory of solving TAP equations for Ising models with general invariant random matrices
• Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing
• Optimal errors and phase transitions in high-dimensional generalized linear models
• High-temperature expansions and message passing algorithms
• Multi-Layer Bilinear Generalized Approximate Message Passing

Cited In (2)

• The decimation scheme for symmetric matrix factorization
• Matrix denoising: Bayes-optimal estimators via low-degree polynomials

This page was built for publication: Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5101092)