Low-rank regularization in two-sided matrix regression
From MaRDI portal
Cites work
- A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers
- Adaptive estimation of the rank of the coefficient matrix in high-dimensional multivariate response regression models
- Assigning topics to documents by successive projections
- Autoregressive models for matrix-valued time series
- Compressed sensing
- Consistency of trace norm minimization
- Estimation of (near) low-rank matrices with noise and high-dimensional scaling
- Estimation of high-dimensional low-rank matrices
- High-dimensional covariance matrix estimation in approximate factor models
- High-dimensional probability. An introduction with applications in data science
- Low rank multivariate regression
- Matrix Autoregressive Spatio-Temporal Models
- Minimal penalties for Gaussian model selection
- Minimax Rates of Estimation for High-Dimensional Linear Regression Over \ell_q-Balls
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- On Cross-Validation for Sparse Reduced Rank Regression
- Optimal estimation of sparse topic models
- Optimal selection of reduced rank estimators of high-dimensional matrices
- Rate minimaxity of the Lasso and Dantzig selector for the \(l_{q}\) loss in \(l_{r}\) balls
- Reduced rank regression via adaptive nuclear norm penalization
- Robust matrix completion
- Simultaneous analysis of Lasso and Dantzig selector
- Structured matrix estimation and completion
- Support union recovery in high-dimensional multivariate regression
This page was built for publication: Low-rank regularization in two-sided matrix regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6979894)
