The decimation scheme for symmetric matrix factorization

DOI10.1088/1751-8121/AD2299MaRDI QIDQ6190382zbMATH OpenOpenAlexWikidataFDO

Authors Francesco Camilli, Marc Mézard

Publication date 5 March 2024

Published in Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2307.16564

zbMATH Keywords

associative memoriesdecimation schemehigh-dimensional inferenceHopfield modelmatrix factorization

Mathematics Subject Classification ID

Computer science (68-XX) Statistical mechanics, structure of matter (82-XX)

Recommendations

• Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Fundamental limits of symmetric low-rank matrix estimation
• Estimation of low-rank matrices via approximate message passing
• Iterative reconstruction of rank-one matrices in noise

Cites work

• A CDMA multiuser detection algorithm on the basis of belief propagation
• Addition of certain non-commuting random variables
• Bilinear Generalized Approximate Message Passing—Part I: Derivation
• Bilinear Generalized Approximate Message Passing—Part II: Applications
• Dictionary Learning Algorithms for Sparse Representation
• Dreaming neural networks: rigorous results
• Eigenvalues of large sample covariance matrices of spiked population models
• Fundamental limits of detection in the spiked Wigner model
• Fundamental limits of symmetric low-rank matrix estimation
• Iterative reconstruction of rank-one matrices in noise
• Multi-Layer Bilinear Generalized Approximate Message Passing
• Neural networks and physical systems with emergent collective computational abilities
• On sample eigenvalues in a generalized spiked population model
• On the distribution of the largest eigenvalue in principal components analysis
• Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
• Robust principal component analysis?
• Rotational Invariant Estimator for General Noisy Matrices
• Self-organization and associative memory
• Statistical mechanics of Hopfield-like neural networks with modified interactions
• The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
• The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• The largest eigenvalue of rank one deformation of large Wigner matrices
• The largest eigenvalue of small rank perturbations of Hermitian random matrices
• The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• The singular values and vectors of low rank perturbations of large rectangular random matrices

Cited in

(3)

• Matrix denoising: Bayes-optimal estimators via low-degree polynomials
• Rectangular rotational invariant estimator for high-rank matrix estimation
• A multiscale cavity method for sublinear-rank symmetric matrix factorization

This page was built for publication: The decimation scheme for symmetric matrix factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6190382)