Matrix completion via max-norm constrained optimization

DOI10.1214/16-EJS1147zbMath1342.62091arXiv1303.0341MaRDI QIDQ302432

T. Tony Cai, Wen-Xin Zhou

Publication date: 5 July 2016

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1303.0341

zbMATH Keywords

matrix completion; sparsity; compressed sensing; low-rank matrix; max-norm constrained minimization; minimax optimality; non-uniform sampling

Mathematics Subject Classification ID

62H12: Estimation in multivariate analysis

62J99: Linear inference, regression

15A83: Matrix completion problems

Related Items

Regularization and the small-ball method II: complexity dependent error rates, Matrix Completion under Low-Rank Missing Mechanism, Unnamed Item, Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization, Deterministic Tensor Completion with Hypergraph Expanders, Matrix Completion With Covariate Information, Recovery of low-rank matrices based on the rank null space properties, Matrix completion under complex survey sampling, Covariate-assisted matrix completion with multiple structural breaks, Geometric inference for general high-dimensional linear inverse problems, Max-norm optimization for robust matrix recovery, Robust matrix completion, Matrix completion by singular value thresholding: sharp bounds, Adaptive multinomial matrix completion, Adaptive confidence sets for matrix completion, Cross: efficient low-rank tensor completion, Online optimization for max-norm regularization, Robust Schatten-\(p\) norm based approach for tensor completion, Structured matrix estimation and completion

Uses Software

• GADMM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Gradient methods for minimizing composite functions
• Von Neumann entropy penalization and low-rank matrix estimation
• 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
• Max-norm optimization for robust matrix recovery
• User-friendly tail bounds for sums of random matrices
• Complexity measures of sign matrices
• Construction of high-order deceptive functions using low-order Walsh coefficients
• Information-theoretic determination of minimax rates of convergence
• Rank estimation in missing data matrix problems
• Rank penalized estimators for high-dimensional matrices
• Noisy low-rank matrix completion with general sampling distribution
• Generalized alternating direction method of multipliers: new theoretical insights and applications
• Exact matrix completion via convex optimization
• A Max-Norm Constrained Minimization Approach to 1-Bit Matrix Completion
• Uniqueness of Low-Rank Matrix Completion by Rigidity Theory
• Scaled sparse linear regression
• Interior-Point Method for Nuclear Norm Approximation with Application to System Identification
• 10.1162/153244303321897690
• 1-Bit matrix completion
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• A Simpler Approach to Matrix Completion
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Learning Theory
• Computational enhancements in low-rank semidefinite programming