Statistically optimal firstorder algorithms: a proof via orthogonalization

DOI10.1093/IMAIAI/IAAE027MaRDI QIDQ6638533zbMATH OpenFDO

Authors Andrea Montanari, Yuchen Wu

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/IAAE027

zbMATH Keywords

approximate message passingfirst-order algorithmlow-rank matrix estimationphase retrieval

Mathematics Subject Classification ID

Statistics (62-XX)

Recommendations

• On the finite-sample analysis of -estimators
• On the finite-sample analysis of \(\Theta\)-estimators
• Estimation of low-rank matrices via approximate message passing
• Fast global convergence of gradient methods for high-dimensional statistical recovery

Cited in

(5)

• Optimality of approximate message passing for spiked matrix models with rotationally invariant noise
• Linear operator approximate message passing (OpAMP)
• Spectral estimators for structured generalized linear models via approximate message passing
• Entrywise dynamics and universality of general first order methods
• Uncertainty quantification for iterative algorithms in linear models with application to early stopping

This page was built for publication: Statistically optimal firstorder algorithms: a proof via orthogonalization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6638533)