Optimal discriminant analysis in high-dimensional latent factor models
From MaRDI portal
Publication:6136589
Abstract: In high-dimensional classification problems, a commonly used approach is to first project the high-dimensional features into a lower dimensional space, and base the classification on the resulting lower dimensional projections. In this paper, we formulate a latent-variable model with a hidden low-dimensional structure to justify this two-step procedure and to guide which projection to choose. We propose a computationally efficient classifier that takes certain principal components (PCs) of the observed features as projections, with the number of retained PCs selected in a data-driven way. A general theory is established for analyzing such two-step classifiers based on any projections. We derive explicit rates of convergence of the excess risk of the proposed PC-based classifier. The obtained rates are further shown to be optimal up to logarithmic factors in the minimax sense. Our theory allows the lower-dimension to grow with the sample size and is also valid even when the feature dimension (greatly) exceeds the sample size. Extensive simulations corroborate our theoretical findings. The proposed method also performs favorably relative to other existing discriminant methods on three real data examples.
Recommendations
- High-Dimensional Discriminant Analysis
- Optimal Feature Selection in High-Dimensional Discriminant Analysis
- High Dimensional Linear Discriminant Analysis: Optimality, Adaptive Algorithm and Missing Data
- High-dimensional linear discriminant analysis using nonparametric methods
- Factorial discriminant analysis and probabilistic models
- The Dantzig discriminant analysis with high dimensional data
- High dimensional discrimination analysis via a semiparametric model
- Bayesian discriminant analysis using a high dimensional predictor
- Dynamic linear discriminant analysis in high dimensional space
Cites work
- scientific article; zbMATH DE number 893887 (Why is no real title available?)
- scientific article; zbMATH DE number 7415120 (Why is no real title available?)
- A convex optimization approach to high-dimensional sparse quadratic discriminant analysis
- A direct approach to sparse discriminant analysis in ultra-high dimensions
- A direct estimation approach to sparse linear discriminant analysis
- Adaptive estimation in structured factor models with applications to overlapping clustering
- Adaptive estimation of the rank of the coefficient matrix in high-dimensional multivariate response regression models
- Classification with many classes: challenges and pluses
- Classifiers of support vector machine type with \(\ell_1\) complexity regularization
- Dimension Reduction for Classification with Gene Expression Microarray Data
- Dimension reduction strategies for analyzing global gene expression data with a response
- Double/debiased machine learning for treatment and structural parameters
- Forecasting Using Principal Components From a Large Number of Predictors
- Forecasting economic time series using targeted predictors
- Functional Classification in Hilbert Spaces
- High Dimensional Linear Discriminant Analysis: Optimality, Adaptive Algorithm and Missing Data
- High-dimensional classification using features annealed independence rules
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- Minimax sparse principal subspace estimation in high dimensions
- Modern Multivariate Statistical Techniques
- Multiclass sparse discriminant analysis
- Optimal aggregation of classifiers in statistical learning.
- Optimal discriminant analysis in high-dimensional latent factor models
- PLS Dimension Reduction for Classification with Microarray Data
- Partial Factor Modeling: Predictor-Dependent Shrinkage for Linear Regression
- Penalized classification using Fisher's linear discriminant
- Prediction by Supervised Principal Components
- Sparse linear discriminant analysis by thresholding for high dimensional data
- Sparse models and methods for optimal instruments with an application to eminent domain
- Statistical analysis of factor models of high dimension
- Sufficient forecasting using factor models
- Supervised principal component analysis: visualization, classification and regression on subspaces and submanifolds
- Support vector machines with a reject option
Cited in
(3)
This page was built for publication: Optimal discriminant analysis in high-dimensional latent factor models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136589)
