Low-Rank Optimization with Trace Norm Penalty

DOI10.1137/110859646zbMath1286.65078arXiv1112.2318OpenAlexW1998367754MaRDI QIDQ5408213

Gilles Meyer, Bamdev Mishra, Francis Bach, Rodolphe J. Sepulchre

Publication date: 9 April 2014

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1112.2318

zbMATH Keywords

algorithmconvergencenumerical examplesmatrix completiontrust regionRiemannian optimizationtrace normmultivariate linear regressionregularization pathpredictor-corrector on quotient manifold

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Numerical mathematical programming methods (65K05) Convex programming (90C25) Interior-point methods (90C51) Matrix completion problems (15A83)

Related Items (27)

Sparse latent factor regression models for genome-wide and epigenome-wide association studies ⋮ GNMR: A Provable One-Line Algorithm for Low Rank Matrix Recovery ⋮ Convergence Results for Projected Line-Search Methods on Varieties of Low-Rank Matrices Via Łojasiewicz Inequality ⋮ Sparse reduced-rank regression for simultaneous rank and variable selection via manifold optimization ⋮ A Riemannian Gradient Sampling Algorithm for Nonsmooth Optimization on Manifolds ⋮ An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion ⋮ An Equivalence between Critical Points for Rank Constraints Versus Low-Rank Factorizations ⋮ Low-rank retractions: a survey and new results ⋮ Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity ⋮ Two Newton methods on the manifold of fixed-rank matrices endowed with Riemannian quotient geometries ⋮ Fixed-rank matrix factorizations and Riemannian low-rank optimization ⋮ Unnamed Item ⋮ Nonconvex weak sharp minima on Riemannian manifolds ⋮ Scalable incremental nonconvex optimization approach for phase retrieval ⋮ Riemannian gradient descent methods for graph-regularized matrix completion ⋮ Majorized proximal alternating imputation for regularized rank constrained matrix completion ⋮ Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains ⋮ Low-rank dynamic mode decomposition: an exact and tractable solution ⋮ A Riemannian rank-adaptive method for low-rank matrix completion ⋮ Generalized Conditional Gradient for Sparse Estimation ⋮ Semi-blind joint channel estimation and data detection on sphere manifold for MIMO with high-order QAM signaling ⋮ Riemannian Multigrid Line Search for Low-Rank Problems ⋮ On the Convergence of Projected-Gradient Methods with Low-Rank Projections for Smooth Convex Minimization over Trace-Norm Balls and Related Problems ⋮ Orthogonal Rank-One Matrix Pursuit for Low Rank Matrix Completion ⋮ A Riemannian symmetric rank-one trust-region method ⋮ Low-rank matrix completion via preconditioned optimization on the Grassmann manifold ⋮ Optimization on the hierarchical Tucker manifold - applications to tensor completion

Uses Software

• PROPACK
• LMaFit
• Optspace

This page was built for publication: Low-Rank Optimization with Trace Norm Penalty