Regularized Matrix Regression

Abstract

Modern technologies are producing a wealth of data with complex structures. For instance, in two-dimensional digital imaging, flow cytometry, and electroencephalography, matrix type covariates frequently arise when measurements are obtained for each combination of two underlying variables. To address scientific questions arising from those data, new regression methods that take matrices as covariates are needed, and sparsity or other forms of regularization are crucial due to the ultrahigh dimensionality and complex structure of the matrix data. The popular lasso and related regularization methods hinge upon the sparsity of the true signal in terms of the number of its nonzero coefficients. However, for the matrix data, the true signal is often of, or can be well approximated by, a low rank structure. As such, the sparsity is frequently in the form of low rank of the matrix parameters, which may seriously violate the assumption of the classical lasso. In this article, we propose a class of regularized matrix regression methods based on spectral regularization. Highly efficient and scalable estimation algorithm is developed, and a degrees of freedom formula is derived to facilitate model selection along the regularization path. Superior performance of the proposed method is demonstrated on both synthetic and real examples.

27 pages, 5 figure

References in corpus (4)

• Nearly unbiased variable selection under minimax concave penalty
• On the "degrees of freedom" of the lasso
• Tensor Regression with Applications in Neuroimaging Data Analysis
• On dimension folding of matrix- or array-valued statistical objects

Cited by in corpus (23)

• Independent component analysis for tensor-valued data
• Symmetric Bilinear Regression for Signal Subgraph Estimation
• The Singular Value Decomposition, Applications and Beyond
• Broadcasted Nonparametric Tensor Regression
• Factor Models for Matrix-Valued High-Dimensional Time Series
• A Nonlinear Kernel Support Matrix Machine for Matrix Learning
• Proximal MCMC for Bayesian Inference of Constrained and Regularized Estimation
• Adaptive Higher-order Spectral Estimators
• Scalar-on-Image Regression via the Soft-Thresholded Gaussian Process
• Hypothesis Testing of Matrix Graph Model with Application to Brain Connectivity Analysis
• Learning Signal Subgraphs from Longitudinal Brain Networks with Symmetric Bilinear Logistic Regression
• Low-rank matrix estimation in multi-response regression with measurement errors: Statistical and computational guarantees
• Nonparametric Matrix Response Regression with Application to Brain Imaging Data Analysis
• Nonparametric Trace Regression in High Dimensions via Sign Series Representation
• Matrix-Variate Regressions and Envelope Models
• Multivariate functional responses low rank regression with an application to brain imaging data
• Theoretical and Experimental Analyses of Tensor-Based Regression and Classification
• Sparse and Low-Rank High-Order Tensor Regression via Parallel Proximal Method
• Matrix Linear Discriminant Analysis
• Multi-distance Support Matrix Machines
• Covariate-Adjusted Tensor Classification in High-Dimensions
• Regularization parameter selection for low rank matrix recovery
• Tensor Canonical Correlation Analysis with Convergence and Statistical Guarantees