Rank penalized estimators for high-dimensional matrices
From MaRDI portal
Abstract: In this paper we consider the trace regression model. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix corrupted by noise. We propose a new rank penalized estimator of . For this estimator we establish general oracle inequality for the prediction error both in probability and in expectation. We also prove upper bounds for the rank of our estimator. Then, we apply our general results to the problems of matrix completion and matrix regression. In these cases our estimator has a particularly simple form: it is obtained by hard thresholding of the singular values of a matrix constructed from the observations.
Recommendations
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Estimation of high-dimensional low-rank matrices
- Robust low-rank matrix estimation
- Matrix estimation by universal singular value thresholding
- Estimation of (near) low-rank matrices with noise and high-dimensional scaling
Cites work
- A simpler approach to matrix completion
- Consistency of trace norm minimization
- 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
- Low rank multivariate regression
- Matrix completion from noisy entries
- Multivariate reduced-rank regression
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- On spectral learning
- Optimal selection of reduced rank estimators of high-dimensional matrices
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Sharp Oracle Inequalities for High-Dimensional Matrix Prediction
- Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
Cited in
(40)- Trace regression model with simultaneously low rank and row(column) sparse parameter
- Non-asymptotic approach to varying coefficient model
- Low rank multivariate regression
- Robust low-rank matrix estimation
- Double fused Lasso regularized regression with both matrix and vector valued predictors
- Spectral thresholding for the estimation of Markov chain transition operators
- Pivotal estimation via square-root lasso in nonparametric regression
- High dimensional deformed rectangular matrices with applications in matrix denoising
- Optimal graphon estimation in cut distance
- Structured matrix estimation and completion
- Nonparametric estimation of low rank matrix valued function
- Convex optimization learning of faithful Euclidean distance representations in nonlinear dimensionality reduction
- Asymptotic equivalence of quantum state tomography and noisy matrix completion
- Noisy low-rank matrix completion with general sampling distribution
- Optimal large-scale quantum state tomography with Pauli measurements
- Bayesian methods for low-rank matrix estimation: short survey and theoretical study
- High-dimensional consistency of rank estimation criteria in multivariate linear model
- Matrix completion via max-norm constrained optimization
- Consistency of trace norm minimization
- A rank-corrected procedure for matrix completion with fixed basis coefficients
- High-dimensional least square matrix regression
- A semiparametric model for matrix regression
- High-dimensional covariance matrix estimation with missing observations
- Von Neumann entropy penalization and low-rank matrix estimation
- Sharp oracle inequalities in low rank estimation
- Learning Theory
- Estimation of high-dimensional low-rank matrices
- Estimation of (near) low-rank matrices with noise and high-dimensional scaling
- Improved matrix uncertainty selector
- High-dimensional regression with unknown variance
- The rate of convergence for sparse and low-rank quantile trace regression
- Noisy low-rank matrix completion under general bases
- Matrix completion from a computational statistics perspective
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Dynamic Matrix Recovery
- Low solution rank of the matrix LASSO under RIP with consequences for rank-constrained algorithms
- Online network change point detection with missing values and temporal dependence
- A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
- Matrix completion by singular value thresholding: sharp bounds
- Adaptive multinomial matrix completion
This page was built for publication: Rank penalized estimators for high-dimensional matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1952222)
