Nonconvex Robust Low-Rank Matrix Recovery

DOI10.1137/18M1224738MaRDI QIDQ5217366FDOQ5217366

Authors: Xiao Li, Zhihui Zhu, Anthony Man-Cho So, René Vidal 

Publication date: 27 February 2020

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

Full work available at URL: https://arxiv.org/abs/1809.09237

zbMATH Keywords

robust PCAsubgradient methodsharpnessweak convexityrobust low-rank matrix recovery

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Numerical optimization and variational techniques (65K10) Analysis of algorithms and problem complexity (68Q25) Analysis of algorithms (68W40) Nonconvex programming, global optimization (90C26)

Cites Work

• A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
• Variational Analysis
• Title not available (Why is that?)
• Robust principal component analysis?
• Exact matrix completion via convex optimization
• Convergence rate of incremental subgradient algorithms
• Title not available (Why is that?)
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• On convergence rates of subgradient optimization methods
• Strong and Weak Convexity of Sets and Functions
• A framework for robust subspace learning
• Local minima and convergence in low-rank semidefinite programming
• Weak Sharp Minima in Mathematical Programming
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• Restricted $p$-Isometry Properties of Nonconvex Matrix Recovery
• Minimization of unsmooth functionals
• Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming
• Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements
• Guaranteed Matrix Completion via Non-Convex Factorization
• Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
• Fast and near-optimal matrix completion via randomized basis pursuit
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• A perturbation inequality for concave functions of singular values and its applications in low-rank matrix recovery
• The learnability of quantum states
• The non-convex geometry of low-rank matrix optimization
• Subgradient methods for sharp weakly convex functions
• Title not available (Why is that?)
• Global Optimality in Low-Rank Matrix Optimization
• Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval
• On the Quadratic Convergence of the Cubic Regularization Method under a Local Error Bound Condition
• The nonsmooth landscape of phase retrieval
• Non-convex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent

Cited In (30)

• Matrix recovery from nonconvex regularized least absolute deviations
• The global optimization geometry of shallow linear neural networks
• Title not available (Why is that?)
• Title not available (Why is that?)
• Low rank matrix recovery with adversarial sparse noise*
• Robust Low-Rank Tensor Recovery via Nonconvex Singular Value Minimization
• Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
• Sensitivity of low-rank matrix recovery
• A low-rank spectral method for learning Markov models
• Stochastic variance reduced gradient for affine rank minimization problem
• Nonconvex Matrix Factorization From Rank-One Measurements
• Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent
• Non-convex exact community recovery in stochastic block model
• Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods
• Global stability of first-order methods for coercive tame functions
• A new complexity metric for nonconvex rank-one generalized matrix completion
• Scalable robust matrix recovery: Frank-Wolfe meets proximal methods
• Max-norm optimization for robust matrix recovery
• A remark on low rank matrix recovery and noncommutative Bernstein type inequalities
• An Unbiased Approach to Low Rank Recovery
• Low-Rank Matrix Estimation from Rank-One Projections by Unlifted Convex Optimization
• Nonsmooth rank-one matrix factorization landscape
• Recovery of low-rank matrices based on the rank null space properties
• Gradient descent provably escapes saddle points in the training of shallow ReLU networks
• Low-rank and sparse matrix recovery via inexact Newton-like method with non-monotone search
• A modification piecewise convexification method with a classification strategy for box-constrained non-convex optimization programs
• Low-Rank Matrix Recovery via Modified Schatten-$p$ Norm Minimization With Convergence Guarantees
• Stochastic optimization over proximally smooth sets
• Adaptive iterative hard thresholding for low-rank matrix recovery and rank-one measurements
• Low-Rank Matrix Recovery Via Robust Outlier Estimation

Uses Software

• SDPLR

This page was built for publication: Nonconvex Robust Low-Rank Matrix Recovery

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5217366)