Matrix completion by singular value thresholding: sharp bounds

DOI10.1214/15-EJS1076zbMath1323.62047arXiv1502.00146OpenAlexW2963418220MaRDI QIDQ887273

Olga Klopp

Publication date: 28 October 2015

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

Full work available at URL: https://arxiv.org/abs/1502.00146

zbMATH Keywords

matrix completionminimax optimalitylow rank matrix estimation

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Random matrices (probabilistic aspects) (60B20) Random matrices (algebraic aspects) (15B52) Matrix completion problems (15A83)

Related Items

Unnamed Item ⋮ Matrix completion with sparse measurement errors ⋮ Adaptive confidence sets for matrix completion ⋮ A singular value thresholding with diagonal-update algorithm for low-rank matrix completion ⋮ Low-rank model with covariates for count data with missing values ⋮ Numerical comparisons between Bayesian and frequentist low-rank matrix completion: estimation accuracy and uncertainty quantification

Uses Software

• softImpute
• impute

Cites Work

• Unnamed Item
• Unnamed Item
• Matrix completion via max-norm constrained optimization
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Absolute and monotonic norms
• Characterization of the subdifferential of some matrix norms
• A new look at independence
• Rank penalized estimators for high-dimensional matrices
• Matrix estimation by universal singular value thresholding
• Noisy low-rank matrix completion with general sampling distribution
• Exact matrix completion via convex optimization
• A Singular Value Thresholding Algorithm for Matrix Completion
• An iterative hard thresholding estimator for low rank matrix recovery with explicit limiting distribution
• Orthogonal Rank-One Matrix Pursuit for Low Rank Matrix Completion
• 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