Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications

DOI10.1088/1742-5468/aa7284zbMath1462.62324arXiv1701.00858OpenAlexW3105600170WikidataQ59460016 ScholiaQ59460016MaRDI QIDQ3303137

Florent Krzakala, Thibault Lesieur, Lenka Zdeborová

Publication date: 11 August 2020

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

Full work available at URL: https://arxiv.org/abs/1701.00858

zbMATH Keywords

phase transitionmatrix estimation

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Bayesian inference (62F15) Statistical mechanics of random media, disordered materials (including liquid crystals and spin glasses) (82D30) Applications of statistics to physics (62P35) Dynamic and nonequilibrium phase transitions (general) in statistical mechanics (82C26)

Related Items

An optimal statistical and computational framework for generalized tensor estimation, Analyticity of the energy in an Ising spin glass with correlated disorder, Disordered systems insights on computational hardness, Mean-field inference methods for neural networks, Dense limit of the Dawid–Skene model for crowdsourcing and regions of sub-optimality of message passing algorithms, Hamilton-Jacobi equations for inference of matrix tensor products, Estimation of low-rank matrices via approximate message passing, Statistical thresholds for tensor PCA, Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising, Finding one community in a sparse graph, Free Energy Wells and Overlap Gap Property in Sparse PCA, When random tensors meet random matrices, Universality of approximate message passing algorithms, The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference, Exact recovery in the Ising blockmodel, The overlap gap property in principal submatrix recovery, Phase transition in the spiked random tensor with Rademacher prior, Algorithmic thresholds for tensor PCA, Optimal combination of linear and spectral estimators for generalized linear models, Statistical mechanics of low-rank tensor decomposition, Approximate survey propagation for statistical inference, A Unifying Tutorial on Approximate Message Passing, Mismatching as a tool to enhance algorithmic performances of Monte Carlo methods for the planted clique model

Uses Software

• ElemStatLearn
• darch

Cites Work

• Unnamed Item
• Unnamed Item
• High-dimensional analysis of semidefinite relaxations for sparse principal components
• Rigorous inequalities between length and time scales in glassy systems
• Finding one community in a sparse graph
• Finding hidden cliques of size \(\sqrt{N/e}\) in nearly linear time
• Do semidefinite relaxations solve sparse PCA up to the information limit?
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Spectral redemption in clustering sparse networks
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• Least squares quantization in PCM
• Statistical Physics of Spin Glasses and Information Processing
• Statistical mechanics of unsupervised structure recognition
• Optimal unsupervised learning
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Neural networks and physical systems with emergent collective computational abilities.
• A Fast Learning Algorithm for Deep Belief Nets