Robust matrix completion
From MaRDI portal
Publication:682808
DOI10.1007/S00440-016-0736-YzbMATH Open1383.62167arXiv1412.8132OpenAlexW2963831709MaRDI QIDQ682808FDOQ682808
Authors: Olga Klopp, K. Lounici, Alexandre B. Tsybakov 
Publication date: 5 February 2018
Published in: Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)
Abstract: This paper considers the problem of recovery of a low-rank matrix in the situation when most of its entries are not observed and a fraction of observed entries are corrupted. The observations are noisy realizations of the sum of a low rank matrix, which we wish to recover, with a second matrix having a complementary sparse structure such as element-wise or column-wise sparsity. We analyze a class of estimators obtained by solving a constrained convex optimization problem that combines the nuclear norm and a convex relaxation for a sparse constraint. Our results are obtained for the simultaneous presence of random and deterministic patterns in the sampling scheme. We provide guarantees for recovery of low-rank and sparse components from partial and corrupted observations in the presence of noise and show that the obtained rates of convergence are minimax optimal.
Full work available at URL: https://arxiv.org/abs/1412.8132
Recommendations
Cites Work
- Matrix completion from noisy entries
- Statistics for high-dimensional data. Methods, theory and applications.
- Robust principal component analysis?
- Introduction to nonparametric estimation
- Hanson-Wright inequality and sub-Gaussian concentration
- Noisy low-rank matrix completion with general sampling distribution
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Estimation of high-dimensional low-rank matrices
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Rank-Sparsity Incoherence for Matrix Decomposition
- Robust Matrix Decomposition With Sparse Corruptions
- Title not available (Why is that?)
- Noisy matrix decomposition via convex relaxation: optimal rates in high dimensions
- Robust PCA via Outlier Pursuit
- Compressed sensing and matrix completion with constant proportion of corruptions
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- A simpler approach to matrix completion
- Matrix completion via max-norm constrained optimization
- Absolute and monotonic norms
Cited In (54)
- Adaptive multinomial matrix completion
- A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
- Robust tensor completion: equivalent surrogates, error bounds, and algorithms
- Color image inpainting via robust pure quaternion matrix completion: error bound and weighted loss
- Low-rank matrix recovery under heavy-tailed errors
- Noisy matrix decomposition via convex relaxation: optimal rates in high dimensions
- Low permutation-rank matrices: structural properties and noisy completion
- Outlier detection in networks with missing links
- Flexible low-rank statistical modeling with missing data and side information
- Bayesian methods for low-rank matrix estimation: short survey and theoretical study
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Structured matrix estimation and completion
- Matrix estimation by universal singular value thresholding
- Matrix completion with covariate information
- Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization
- Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
- All-in-one robust estimator of the Gaussian mean
- A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
- Collective matrix completion
- Noisy low-rank matrix completion with general sampling distribution
- Robust low-rank matrix estimation
- Tight risk bound for high dimensional time series completion
- Exact matrix completion via convex optimization
- Computing the best approximation over the intersection of a polyhedral set and the doubly nonnegative cone
- High-dimensional VAR with low-rank transition
- A generalized non-convex method for robust tensor completion
- A rank-corrected procedure for matrix completion with fixed basis coefficients
- Low-rank matrix estimation via nonconvex optimization methods in multi-response errors-in-variables regression
- Title not available (Why is that?)
- Matrix completion with noisy entries and outliers
- Robust low-rank matrix completion by Riemannian optimization
- Estimation of matrices with row sparsity
- Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
- Matrix optimization based Euclidean embedding with outliers
- Gradient descent for sparse rank-one matrix completion for crowd-sourced aggregation of sparsely interacting workers
- Nonparametric estimation of low rank matrix valued function
- Matrix factorization for multivariate time series analysis
- Compressed sensing and matrix completion with constant proportion of corruptions
- Optimal estimation and completion of matrices with biclustering structures
- Robust recovery of Robinson property in \(L^p\)-graphons: a cut-norm approach
- Nonlocal robust tensor recovery with nonconvex regularization
- Using side information to reliably learn low-rank matrices from missing and corrupted observations
- Bridging convex and nonconvex optimization in robust PCA: noise, outliers and missing data
- ROP: matrix recovery via rank-one projections
- Practical matrix completion and corruption recovery using proximal alternating robust subspace minimization
- Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
- Sparse recovery under matrix uncertainty
- Optimal cleaning for singular values of cross-covariance matrices
- Inference and uncertainty quantification for noisy matrix completion
- Compressed sensing of low-rank plus sparse matrices
- Main effects and interactions in mixed and incomplete data frames
- Detection thresholds in very sparse matrix completion
- Asymptotic theory for estimating the singular vectors and values of a partially-observed low rank matrix with noise
- Covariate-assisted matrix completion with multiple structural breaks
This page was built for publication: Robust matrix completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q682808)
