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

DOI10.1088/1742-5468/ac7e4cOpenAlexW3206621305WikidataQ114096179 ScholiaQ114096179MaRDI QIDQ5101092

Florent Krzakala, Lenka Zdeborová, Marc Mézard, Antoine Maillard

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

zbMATH Keywords

learning theoryspin glassesstatistical inferencerandom matrix theory and extensions

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items

The decimation scheme for symmetric matrix factorization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• Cleaning large correlation matrices: tools from random matrix theory
• Rectangular \(R\)-transform as the limit of rectangular spherical integrals
• Large deviations and stochastic calculus for large random matrices
• Addition of certain non-commuting random variables
• First order asymptotics of matrix integrals; a rigorous approach towards the understanding of matrix models
• Large deviations asymptotics for spherical integrals
• On the large-\(N\) limit of the Itzykson-Zuber integral.
• Universality in polytope phase transitions and message passing algorithms
• Optimal shrinkage of eigenvalues in the spiked covariance model
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Exact matrix completion via convex optimization
• Complexity of random smooth functions on compact manifolds
• Rotational Invariant Estimator for General Noisy Matrices
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
• Hydrodynamical spectral evolution for random matrices
• A theory of solving TAP equations for Ising models with general invariant random matrices
• Robust principal component analysis?
• Differential Operators on a Semisimple Lie Algebra
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• Information, Physics, and Computation
• An Introduction to Random Matrices
• Dictionary Learning Algorithms for Sparse Representation
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• Bilinear Generalized Approximate Message Passing—Part II: Applications
• Introduction to Random Matrices
• The planar approximation. II
• Statistical Physics of Spin Glasses and Information Processing
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• Optimal errors and phase transitions in high-dimensional generalized linear models
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing
• High-temperature expansions and message passing algorithms
• Multi-Layer Bilinear Generalized Approximate Message Passing