An Unbiased Approach to Low Rank Recovery

DOI10.1137/19M1294800MaRDI QIDQ5055687

Carl Olsson, Daniele Gerosa, Marcus Carlsson

Publication date: 9 December 2022

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

Full work available at URL: https://arxiv.org/abs/1909.13363

zbMATH Keywords

nonconvex optimizationlow rank completionquadratic envelope regularization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10)

Cites Work

• Unnamed Item
• Explicit constructions of RIP matrices and related problems
• A simple prior-free method for non-rigid structure-from-motion factorization
• Low rank matrix completion by alternating steepest descent methods
• A remark on regularization in Hilbert spaces
• Convex envelopes for fixed rank approximation
• Global convergence of ADMM in nonconvex nonsmooth optimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Convex low rank approximation
• Von Neumann's trace inequality for Hilbert-Schmidt operators
• Weighted nuclear norm minimization and its applications to low level vision
• On convex envelopes and regularization of non-convex functionals without moving global minima
• Exact matrix completion via convex optimization
• Operator-Lipschitz estimates for the singular value functional calculus
• Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices
• Robust principal component analysis?
• A Singular Value Thresholding Algorithm for Matrix Completion
• Compressed Sensing: How Sharp Is the Restricted Isometry Property?
• Global Convergence of Splitting Methods for Nonconvex Composite Optimization
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Variational Analysis
• Low-Rank Inducing Norms with Optimality Interpretations
• Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm
• Global Optimality in Low-Rank Matrix Optimization
• An unbiased approach to compressed sensing
• On phase retrieval via matrix completion and the estimation of low rank PSD matrices
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• Nonlinear Programming
• Stable signal recovery from incomplete and inaccurate measurements

This page was built for publication: An Unbiased Approach to Low Rank Recovery