Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing

DOI10.1109/TSP.2021.3051425MaRDI QIDQ5103351zbMATH OpenOpenAlexFDO

Authors Cong Ma, Yuan-Xin Li, Yuejie Chi

Publication date 23 September 2022

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.05113

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited in

(8)

• GNMR: a provable one-line algorithm for low rank matrix recovery
• Accelerating ill-conditioned low-rank matrix estimation via scaled gradient descent
• Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy
• Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion
• Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization
• On squared-variable formulations
• The power of preconditioning in overparameterized low-rank matrix sensing
• Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult

This page was built for publication: Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5103351)