Noisy low-rank matrix completion with general sampling distribution
From MaRDI portal
Publication:2444669
Abstract: In the present paper, we consider the problem of matrix completion with noise. Unlike previous works, we consider quite general sampling distribution and we do not need to know or to estimate the variance of the noise. Two new nuclear-norm penalized estimators are proposed, one of them of "square-root" type. We analyse their performance under high-dimensional scaling and provide non-asymptotic bounds on the Frobenius norm error. Up to a logarithmic factor, these performance guarantees are minimax optimal in a number of circumstances.
Recommendations
Cites work
- A remark on low rank matrix recovery and noncommutative Bernstein type inequalities
- A simpler approach to matrix completion
- Estimation of (near) low-rank matrices with noise and high-dimensional scaling
- Estimation of high-dimensional low-rank matrices
- Exact matrix completion via convex optimization
- Matrix completion from noisy entries
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Optimal selection of reduced rank estimators of high-dimensional matrices
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Rank penalized estimators for high-dimensional matrices
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Sharp Oracle Inequalities for High-Dimensional Matrix Prediction
- Square-root lasso: pivotal recovery of sparse signals via conic programming
- Statistics for high-dimensional data. Methods, theory and applications.
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- User-friendly tail bounds for sums of random matrices
- Von Neumann entropy penalization and low-rank matrix estimation
Cited in
(93)- Leveraging mixed and incomplete outcomes via reduced-rank modeling
- Double instrumental variable estimation of interaction models with big data
- Adaptive confidence sets for matrix completion
- Cross: efficient low-rank tensor completion
- On the exponentially weighted aggregate with the Laplace prior
- Non-asymptotic approach to varying coefficient model
- Robust low-rank matrix estimation
- Online optimization for max-norm regularization
- Matrix optimization based Euclidean embedding with outliers
- Bridging convex and nonconvex optimization in robust PCA: noise, outliers and missing data
- Spectral thresholding for the estimation of Markov chain transition operators
- Low-rank matrix denoising for count data using unbiased Kullback-Leibler risk estimation
- Proof methods for robust low-rank matrix recovery
- Tight risk bound for high dimensional time series completion
- Augmented Lagrangian methods for convex matrix optimization problems
- Optimal prediction in the linearly transformed spiked model
- Matrix completion with nonconvex regularization: spectral operators and scalable algorithms
- Concentration of tempered posteriors and of their variational approximations
- On the equivalence of inexact proximal ALM and ADMM for a class of convex composite programming
- Parallel integrative learning for large-scale multi-response regression with incomplete outcomes
- Outlier detection in networks with missing links
- One-bit tensor completion via transformed tensor singular value decomposition
- Maximum likelihood estimation of sparse networks with missing observations
- Low-rank model with covariates for count data with missing values
- Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
- Structured matrix estimation and completion
- A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
- Convex optimization learning of faithful Euclidean distance representations in nonlinear dimensionality reduction
- Empirical Bayes matrix completion
- Constructing confidence sets for the matrix completion problem
- Statistically optimal and computationally efficient low rank tensor completion from noisy entries
- A low-rank spectral method for learning Markov models
- Optimal large-scale quantum state tomography with Pauli measurements
- Matrix completion from noisy entries
- Matrix completion via max-norm constrained optimization
- A rank-corrected procedure for matrix completion with fixed basis coefficients
- Estimation of low rank density matrices: bounds in Schatten norms and other distances
- An Adaptive Correction Approach for Tensor Completion
- Estimation of matrices with row sparsity
- Imputation of Mixed Data With Multilevel Singular Value Decomposition
- Low rank estimation of smooth kernels on graphs
- Asymptotic theory for estimating the singular vectors and values of a partially-observed low rank matrix with noise
- Sharp oracle inequalities for square root regularization
- Regularization and the small-ball method. II: Complexity dependent error rates
- Matrix Completion under Low-Rank Missing Mechanism
- Color image inpainting via robust pure quaternion matrix completion: error bound and weighted loss
- Bayesian singular value regularization via a cumulative shrinkage process
- Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization
- Low-rank matrix completion and denoising under Poisson noise
- Matrix completion based on Gaussian parameterized belief propagation
- Matrix denoising for weighted loss functions and heterogeneous signals
- Deterministic tensor completion with hypergraph expanders
- scientific article; zbMATH DE number 7164697 (Why is no real title available?)
- Low permutation-rank matrices: structural properties and noisy completion
- Collective matrix completion
- Inference and uncertainty quantification for noisy matrix completion
- Matrix completion with covariate information
- Multistage convex relaxation approach to rank regularized minimization problems based on equivalent mathematical program with a generalized complementarity constraint
- A simpler approach to matrix completion
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Robust tensor completion: equivalent surrogates, error bounds, and algorithms
- Matrix Completion Methods for Causal Panel Data Models
- A Schur complement based semi-proximal ADMM for convex quadratic conic programming and extensions
- Robust Recommendation via Social Network Enhanced Matrix Completion
- Iterative tensor eigen rank minimization for low-rank tensor completion
- Robust matrix estimations meet Frank-Wolfe algorithm
- A Corrected Tensor Nuclear Norm Minimization Method for Noisy Low-Rank Tensor Completion
- Inference for low-rank models
- A Zero-imputation Approach in Recommendation Systems with Data Missing Heterogeneously
- Noisy low-rank matrix completion under general bases
- Low-rank matrix recovery under heavy-tailed errors
- Matrix completion from a computational statistics perspective
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Robust recovery of Robinson property in L^p-graphons: a cut-norm approach
- Max-norm optimization for robust matrix recovery
- Robust matrix completion
- Noisy matrix completion for longitudinal data with subject- and time-specific covariates
- Co-Factor Analysis of Citation Networks
- Robust Matrix Completion with Heavy-Tailed Noise
- Concentration properties of fractional posterior in 1-bit matrix completion
- Statistical Inference For Noisy Matrix Completion Incorporating Auxiliary Information
- A fast correction approach to tensor robust principal component analysis
- Robust tensor completion from uniformly dithered one-bit observations
- Online network change point detection with missing values and temporal dependence
- Inference for Low-Rank Models Without Estimating the Rank
- Sharp bounds for multiple models in matrix completion
- Recovery performance of PhaseLift for phase retrieval from coded diffraction patterns
- Simultaneous Estimation of Connectivity and Dimensionality in Samples of Networks
- Estimation and inference for unbalanced panel data models with interactive fixed effects
- Dynamic mode decomposition via difference-of-convex principal component analysis
- Optimal rates for smooth nonlinear matrix completion via low-rank approximation
- Matrix completion by singular value thresholding: sharp bounds
- Adaptive multinomial matrix completion
This page was built for publication: Noisy low-rank matrix completion with general sampling distribution
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2444669)
