Prediction and estimation consistency of sparse multi-class penalized optimal scoring
The results on the consistency of group-Lasso estimators in linear regression cannot be applied to the penalized optimal scoring problem. The key difficulty is that linear model for the multiple response \(Y\) does not hold, and the dependency between the random covariates in \(X\) and the residual terms in \(E=Y-XB.\) The paper under review overcomes these challenges by using sub-exponential concentration bounds, and exploiting the decomposition of marginal covariance matrix. Main contributions are as follows. 1. A coordinate-sparse multi-class optimal scoring problem is formulated as the penalized multiple response linear regression problem. 2. The concentration bound is derived for the maximal row \(l_2\) norm of \(n^{-1}X^\top E\). Here \(X\) and \(E\) could be non-Gaussian and/or correlated. 3. Out-of-sample prediction and estimation bounds are derived for sparse multi-class optimal scoring problem which allow both the number of features and the number of classes to grow with the sample size. Bounds of two types are obtained: (a) slow-rate bounds which make no assumptions on the correlation structure of \(X\) or the sparsity of \(B\), and (b) fast-rate bounds which lead to faster convergence rates, but rely on exact sparsity of \(B\) and restricted eigenvalue condition. 4. It is shown that out-of-sample prediction consistency implies classification consistency, and finite-sample bounds are derived on misclassification error rate of multi-class penalized optimal scoring problem.
- Erratum to: ``Prediction and estimation consistency of sparse multi-class penalized optimal scoring
- Robust and sparse multigroup classification by the optimal scoring approach
- Proximal Methods for Sparse Optimal Scoring and Discriminant Analysis
- Multiclass Classification by Sparse Multinomial Logistic Regression
- Sparse classification: a scalable discrete optimization perspective
- Learning multi-label predictors under sparsity budget
- A penalized optimization method for classification
- Binary Credal Classification Under Sparsity Constraints
- A direct approach to sparse discriminant analysis in ultra-high dimensions
- A direct estimation approach to sparse linear discriminant analysis
- A tail inequality for quadratic forms of subgaussian random vectors
- A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers
- A unified theory of confidence regions and testing for high-dimensional estimating equations
- Bayesian variable selection for globally sparse probabilistic PCA
- CODA: high dimensional copula discriminant analysis
- Covariate-adjusted tensor classification in high dimensions
- Exponential screening and optimal rates of sparse estimation
- Flexible Discriminant Analysis by Optimal Scoring
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 3673370 (Why is no real title available?)
- scientific article; zbMATH DE number 2118472 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 6438182 (Why is no real title available?)
- L1 least squares for sparse high-dimensional LDA
- Model Selection and Estimation in Regression with Grouped Variables
- On the conditions used to prove oracle results for the Lasso
- On the prediction performance of the Lasso
- Optimal Feature Selection in High-Dimensional Discriminant Analysis
- Optimal variable selection in multi-group sparse discriminant analysis
- Oracle inequalities and optimal inference under group sparsity
- Oracle inequalities for high-dimensional prediction
- Penalized classification using Fisher's linear discriminant
- Penalized discriminant analysis
- Persistene in high-dimensional linear predictor-selection and the virtue of overparametrization
- Prediction error bounds for linear regression with the TREX
- Reconstruction From Anisotropic Random Measurements
- Restricted eigenvalue properties for correlated Gaussian designs
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
- Simultaneous analysis of Lasso and Dantzig selector
- Some sharp performance bounds for least squares regression with L₁ regularization
- Sparse quadratic classification rules via linear dimension reduction
- Sparsity oracle inequalities for the Lasso
- Statistics for high-dimensional data. Methods, theory and applications.
- Support union recovery in high-dimensional multivariate regression
- Robust and sparse multigroup classification by the optimal scoring approach
- eSPA+: Scalable Entropy-Optimal Machine Learning Classification for Small Data Problems
- Joint association and classification analysis of multi‐view data
- Sparse overlapped linear discriminant analysis
- Asymmetric canonical correlation analysis of Riemannian and high-dimensional data
- Optimal variable selection in multi-group sparse discriminant analysis
This page was built for publication: Prediction and estimation consistency of sparse multi-class penalized optimal scoring
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2278663)
