Alternating minimization for generalized rank-1 matrix sensing: sharp predictions from a random initialization

DOI10.1093/IMAIAI/IAAE025MaRDI QIDQ6638531zbMATH OpenFDO

Authors Kabir Aladin Chandrasekher, Mengqi Lou, Ashwin Pananjady

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/IAAE025

zbMATH Keywords

alternating minimizationmatrix sensingnon-convex optimizationsharp error prediction

Mathematics Subject Classification ID

Statistics (62-XX) Nonconvex programming, global optimization (90C26)

Recommendations

• Sharp global convergence guarantees for iterative nonconvex optimization with random data
• Iterative reconstruction of rank-one matrices in noise
• Low-rank matrix completion using alternating minimization
• Composite optimization for robust rank one bilinear sensing

Cited in

(4)

• High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance
• Asymptotic dynamics of alternating minimization for bilinear regression
• The power of preconditioning in overparameterized low-rank matrix sensing
• Uncertainty quantification for iterative algorithms in linear models with application to early stopping

This page was built for publication: Alternating minimization for generalized rank-1 matrix sensing: sharp predictions from a random initialization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6638531)