Covariate-adjusted tensor classification in high dimensions
From MaRDI portal
Abstract: In contemporary scientific research, it is of great interest to predict a categorical response based on a high-dimensional tensor (i.e. multi-dimensional array) and additional covariates. This mixture of different types of data leads to challenges in statistical analysis. Motivated by applications in science and engineering, we propose a comprehensive and interpretable discriminant analysis model, called CATCH model (in short for Covariate-Adjusted Tensor Classification in High-dimensions), which efficiently integrates the covariates and the tensor to predict the categorical outcome. The CATCH model jointly models the relationships among the covariates, the tensor predictor, and the categorical response. More importantly, it preserves and utilizes the structures of the data for maximum interpretability and optimal prediction. To tackle the new computational and statistical challenges arising from the intimidating tensor dimensions, we propose a penalized approach to select a subset of tensor predictor entries that has direct discriminative effect after adjusting for covariates. We further develop an efficient algorithm that takes advantage of the tensor structure. Theoretical results confirm that our method achieves variable selection consistency and optimal classification error, even when the tensor dimension is much larger than the sample size. The superior performance of our method over existing methods is demonstrated in extensive simulated and real data examples.
Recommendations
- High dimensional classification for spatially dependent data with application to neuroimaging
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- Tensor envelope mixture model for simultaneous clustering and multiway dimension reduction
- Bayesian tensor regression
- Partially Observed Dynamic Tensor Response Regression
Cites work
- scientific article; zbMATH DE number 784362 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1391247 (Why is no real title available?)
- scientific article; zbMATH DE number 6438182 (Why is no real title available?)
- A direct approach to sparse discriminant analysis in ultra-high dimensions
- A direct estimation approach to sparse linear discriminant analysis
- A feature selection Newton method for support vector machine classification
- A road to classification in high dimensional space: the regularized optimal affine discriminant
- A well-conditioned estimator for large-dimensional covariance matrices
- CODA: high dimensional copula discriminant analysis
- Classifier technology and the illusion of progress
- Consistency of the group Lasso and multiple kernel learning
- Covariance-enhanced discriminant analysis
- Discriminant analysis through a semiparametric model
- Gemini: graph estimation with matrix variate normal instances
- High-dimensional classification using features annealed independence rules
- Maximum likelihood estimation for the tensor normal distribution: Algorithm, minimum sample size, and empirical bias and dispersion
- Model Selection and Estimation in Regression with Grouped Variables
- Multilinear tensor regression for longitudinal relational data
- On Estimation of Covariance Matrices With Kronecker Product Structure
- On Partial Sufficient Dimension Reduction With Applications to Partially Linear Multi-Index Models
- On Tensors, Sparsity, and Nonnegative Factorizations
- Penalized classification using Fisher's linear discriminant
- Provable sparse tensor decomposition
- QUADRO: a supervised dimension reduction method via Rayleigh quotient optimization
- Random forests
- Regularized Matrix Regression
- Some theory for Fisher's linear discriminant function, `naive Bayes', and some alternatives when there are many more variables than observations
- Sparse Quadratic Discriminant Analysis For High Dimensional Data
- Sparse linear discriminant analysis by thresholding for high dimensional data
- Sparse semiparametric discriminant analysis
- Sparse tensor discriminant analysis
- Structured Lasso for regression with matrix covariates
- Sufficient dimension reduction in regressions with categorical predictors
- Support-vector networks
- Tensor Decompositions and Applications
- Tensor Regression with Applications in Neuroimaging Data Analysis
- Tensor SVD: Statistical and Computational Limits
- Tensor-on-Tensor Regression
- The elements of statistical learning. Data mining, inference, and prediction
- The mle algorithm for the matrix normal distribution
- Theoretical and experimental analyses of tensor-based regression and classification
Cited in
(26)- A portmanteau local feature discrimination approach to the classification with high-dimensional matrix-variate data
- Model-Based Tensor Low-Rank Clustering
- Parsimonious Tensor Discriminant Analysis
- Covariate-Assisted Sparse Tensor Completion
- ISLET: fast and optimal low-rank tensor regression via importance sketching
- Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
- Prediction and estimation consistency of sparse multi-class penalized optimal scoring
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- A general framework for tensor screening through smoothing
- High dimensional classification for spatially dependent data with application to neuroimaging
- Bayesian Regression Analysis of Skewed Tensor Responses
- Tensor envelope mixture model for simultaneous clustering and multiway dimension reduction
- Covariance structure approximation via gLasso in high-dimensional supervised classification
- Dynamic modeling and online monitoring of tensor data streams with application to passenger flow surveillance
- catch
- Statistical performance of quantile tensor regression with convex regularization
- Efficient computation for differential network analysis with applications to quadratic discriminant analysis
- Scaled Partial Envelope Model in Multivariate Linear Regression
- Statistical inference on the significance of rows and columns for matrix-valued data in an additive model
- Likelihood-Based Dimension Folding on Tensor Data
- Efficient estimation of reduced-rank partial envelope model in multivariate linear regression
- Multiway Sparse Distance Weighted Discrimination
- Fast and Separable Estimation in High-Dimensional Tensor Gaussian Graphical Models
- Groupwise partial envelope model: efficient estimation in multivariate linear regression
- Alteration detection of tensor dependence structure via sparsity-exploited reranking algorithm
- Efficient simultaneous partial envelope model in multivariate linear regression
Describes a project that uses
Uses Software
This page was built for publication: Covariate-adjusted tensor classification in high dimensions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q131930)
