Dynamic Supervised Principal Component Analysis for Classification
- 17 April 2025
- journal article
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 34 (4) , 1446-1455
Abstract
This paper introduces a novel framework for dynamic classification in high dimensional spaces, addressing the evolving nature of class distributions over time or other index variables. Traditional discriminant analysis techniques are adapted to learn dynamic decision rules with respect to the index variable. In particular, we propose and study a new supervised dimension reduction method employing kernel smoothing to identify the optimal subspace, and provide a comprehensive examination of this approach for both linear discriminant analysis and quadratic discriminant analysis. We illustrate the effectiveness of the proposed methods through numerical simulations and real data examples. The results show considerable improvements in classification accuracy and computational efficiency. This work contributes to the field by offering a robust and adaptive solution to the challenges of scalability and non-staticity in high-dimensional data classification.Keywords
All Related Versions
Funding Information
- National Institutes of Health (1R21AG074205-01)
- National Science Foundation (DMS-2245381)
- Simons Foundation (524432)
- National Science Foundation (DMR 2242925)
- National Institutes of Health (1R01 CA260399)
This publication has 31 references indexed in Scilit:
- Dynamic Principal Component Analysis in High DimensionsJournal of the American Statistical Association, 2022
- Quadratic discriminant analysis by projectionJournal of Multivariate Analysis, 2022
- Nonparametric estimation of large covariance matrices with conditional sparsityJournal of Econometrics, 2021
- A new semiparametric estimation approach for large dynamic covariance matrices with multiple conditioning variablesJournal of Econometrics, 2019
- Dynamic Covariance ModelsJournal of the American Statistical Association, 2016
- A Note On the Connection and Equivalence of Three Sparse Linear Discriminant Analysis MethodsTechnometrics, 2013
- A direct approach to sparse discriminant analysis in ultra-high dimensionsBiometrika, 2012
- Sparse linear discriminant analysis for simultaneous testing for the significance of a gene set/pathway and gene selectionBioinformatics, 2009
- Regularized linear discriminant analysis and its application in microarraysBiostatistics, 2006
- Diagnosis of multiple cancer types by shrunken centroids of gene expressionProceedings of the National Academy of Sciences of the United States of America, 2002