Approximate message passing for orthogonally invariant ensembles: multivariate non-linearities and spectral initialization

DOI10.1093/IMAIAI/IAAE024MaRDI QIDQ6638530zbMATH OpenFDO

Authors Xinyi Zhong, Tianhao Wang, Zhou Fan

Publication date 14 November 2024

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1093/IMAIAI/IAAE024

zbMATH Keywords

AMP algorithmsfree probabilitylow-rank matrix estimationspiked random matrices

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Data structures (68P05)

Recommendations

• Approximate message passing algorithms for rotationally invariant matrices
• Approximate message passing with spectral initialization for generalized linear models*
• Universality of approximate message passing algorithms
• Estimation of low-rank matrices via approximate message passing

Cited in

(8)

• Approximate message passing with spectral initialization for generalized linear models*
• Universality of approximate message passing with semirandom matrices
• Optimality of approximate message passing for spiked matrix models with rotationally invariant noise
• Linear operator approximate message passing (OpAMP)
• Rectangular rotational invariant estimator for high-rank matrix estimation
• A leave-one-out approach to approximate message passing
• Precise asymptotics for spectral methods in mixed generalized linear models
• A nonasymptotic distributional theory of approximate message passing for sparse and robust regression

This page was built for publication: Approximate message passing for orthogonally invariant ensembles: multivariate non-linearities and spectral initialization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6638530)