Nonconvex Matrix Factorization From Rank-One Measurements

DOI10.1109/TIT.2021.3050427zbMath1473.65050arXiv1802.06286OpenAlexW3119735511MaRDI QIDQ5001494

Yuejie Chi, Yuan-Xin Li, Yuxin Chen, Cong Ma

Publication date: 22 July 2021

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1802.06286

zbMATH Keywords

recovering low-rank matricesvanilla gradient descentminimization of nonconvex least-squares loss functionnear-optimal computational complexitynear-optimal sample complexityrandom rank-one measurements

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Numerical methods for matrix equations (65F45)

Related Items

Improved Performance Guarantees for Orthogonal Group Synchronization via Generalized Power Method, Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval, Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence, Low-Rank Matrix Estimation from Rank-One Projections by Unlifted Convex Optimization, Unnamed Item