ROP: matrix recovery via rank-one projections

DOI10.1214/14-AOS1267zbMath1308.62120arXiv1310.5791OpenAlexW3098494111MaRDI QIDQ2338922

Anru Zhang

Publication date: 27 March 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1310.5791

zbMATH Keywords

optimal rate of convergencelow-rank matrix recoveryspiked covariance matrixconstrained nuclear norm minimizationrank-one projectionrestricted uniform boundedness

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Image analysis in multivariate analysis (62H35) Minimax procedures in statistical decision theory (62C20)

Related Items (26)

A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery ⋮ Optimal large-scale quantum state tomography with Pauli measurements ⋮ Almost everywhere injectivity conditions for the matrix recovery problem ⋮ Iterative hard thresholding for low-rank recovery from rank-one projections ⋮ Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution ⋮ Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution Under Random Designs ⋮ Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval ⋮ On signal detection and confidence sets for low rank inference problems ⋮ Performance bounds of the intensity-based estimators for noisy phase retrieval ⋮ Time for dithering: fast and quantized random embeddings via the restricted isometry property ⋮ Adaptive iterative hard thresholding for low-rank matrix recovery and rank-one measurements ⋮ A global exact penalty for rank-constrained optimization problem and applications ⋮ Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems ⋮ Norm and Trace Estimation with Random Rank-one Vectors ⋮ Matrix factorization for multivariate time series analysis ⋮ Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach ⋮ Jointly low-rank and bisparse recovery: Questions and partial answers ⋮ Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence ⋮ Efficient Matrix Sensing Using Rank-1 Gaussian Measurements ⋮ Truncated sparse approximation property and truncated \(q\)-norm minimization ⋮ Generalized phase retrieval: measurement number, matrix recovery and beyond ⋮ ℓ ₁ − αℓ ₂ minimization methods for signal and image reconstruction with impulsive noise removal ⋮ Low-Rank Matrix Estimation from Rank-One Projections by Unlifted Convex Optimization ⋮ ROP: matrix recovery via rank-one projections ⋮ The Dantzig selector: recovery of signal via ℓ ₁ − αℓ ₂ minimization ⋮ ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching

Uses Software

• CVX
• PhaseLift
• Eigenstrat

Cites Work

• High dimensional covariance matrix estimation using a factor model
• The bounds of restricted isometry constants for low rank matrices recovery
• Minimax bounds for sparse PCA with noisy high-dimensional data
• Estimation of high-dimensional low-rank matrices
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Spectral norm of products of random and deterministic matrices
• Distance matrix completion by numerical optimization
• Adaptive estimation of a quadratic functional by model selection.
• On the distribution of the largest eigenvalue in principal components analysis
• Sharp RIP bound for sparse signal and low-rank matrix recovery
• ROP: matrix recovery via rank-one projections
• Optimal estimation and rank detection for sparse spiked covariance matrices
• Asymptotic equivalence of quantum state tomography and noisy matrix completion
• Sparse PCA: optimal rates and adaptive estimation
• Exact matrix completion via convex optimization
• PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
• Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming
• Sketching Sparse Matrices, Covariances, and Graphs via Tensor Products
• Robust principal component analysis?
• Graph Implementations for Nonsmooth Convex Programs
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Nonparametric Detection of Signals by Information Theoretic Criteria: Performance Analysis and an Improved Estimator
• Compressed Sensing and Affine Rank Minimization Under Restricted Isometry
• On Recovery of Sparse Signals Via $\ell _{1}$ Minimization
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Sparse Representation of a Polytope and Recovery of Sparse Signals and Low-Rank Matrices
• A Simpler Approach to Matrix Completion

This page was built for publication: ROP: matrix recovery via rank-one projections