Matrix completion based on Gaussian parameterized belief propagation

DOI10.1088/1742-5468/AC21C9MaRDI QIDQ5158906zbMATH OpenOpenAlexFDO

Authors Koki Okajima, Yoshiyuki Kabashima

Publication date 26 October 2021

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

Full work available at URL https://arxiv.org/abs/2105.00233

zbMATH Keywords

message-passing algorithms

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Recommendations

• Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm
• An alternating direction algorithm for matrix completion with nonnegative factors
• Orthogonal rank-one matrix pursuit for low rank matrix completion
• Noisy low-rank matrix completion with general sampling distribution
• Approximate matrix completion based on cavity method

Cites work

• A CDMA multiuser detection algorithm on the basis of belief propagation
• Approximate matrix completion based on cavity method
• First eigenvalue/eigenvector in sparse random symmetric matrices: influences of degree fluctuation
• Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
• scientific article; zbMATH DE number 6438182 (Why is no real title available?)
• Information, Physics, and Computation
• Low-rank matrix completion using alternating minimization
• Matrix completion from noisy entries
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Statistical Physics of Spin Glasses and Information Processing

Cited in

(1)

• Graphical model for factorization and completion of relatively high rank tensors by sparse sampling

This page was built for publication: Matrix completion based on Gaussian parameterized belief propagation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5158906)