A Riemannian rank-adaptive method for low-rank matrix completion

DOI10.1007/S10589-021-00328-WzbMath1484.90110arXiv2103.14768OpenAlexW3213035342WikidataQ115384040 ScholiaQ115384040MaRDI QIDQ2070331

Bin Gao, Pierre-Antoine Absil

Publication date: 24 January 2022

Published in: Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.14768

zbMATH Keywords

matrix completionRiemannian optimizationlow-rankfixed-rank manifoldbounded-rank matricesrank-adaptive

Mathematics Subject Classification ID

Nonlinear programming (90C30)

Related Items (7)

Riemannian Conjugate Gradient Methods: General Framework and Specific Algorithms with Convergence Analyses ⋮ A universal rank approximation method for matrix completion ⋮ Low-rank tensor methods for partial differential equations ⋮ Stable Rank-Adaptive Dynamically Orthogonal Runge–Kutta Schemes ⋮ T-product factorization based method for matrix and tensor completion problems ⋮ A feasible method for general convex low-rank SDP problems ⋮ Fully adaptive structure-preserving hyper-reduction of parametric Hamiltonian systems

Uses Software

• RTRMC

Cites Work

• Unnamed Item
• Low rank matrix completion by alternating steepest descent methods
• A brief introduction to manifold optimization
• Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
• Guarantees of Riemannian Optimization for Low Rank Matrix Recovery
• Low-Rank Matrix Completion by Riemannian Optimization
• Convergence Results for Projected Line-Search Methods on Varieties of Low-Rank Matrices Via Łojasiewicz Inequality
• Geometric Methods on Low-Rank Matrix and Tensor Manifolds
• Two-Point Step Size Gradient Methods
• The Riemannian Barzilai–Borwein method with nonmonotone line search and the matrix geometric mean computation
• Riemannian Optimization on the Symplectic Stiefel Manifold
• Global rates of convergence for nonconvex optimization on manifolds
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Low-Rank Optimization with Trace Norm Penalty

This page was built for publication: A Riemannian rank-adaptive method for low-rank matrix completion