PLFD - Portmanteau Local Feature Discrimination for Matrix-Variate Data
The portmanteau local feature discriminant approach first identifies the local discriminant features and their differential structures, then constructs the discriminant rule by pooling the identified local features together. This method is applicable to high-dimensional matrix-variate data. See the paper by Xu, Luo and Chen (2021, <doi:10/gmt2gd>).
Last updated 2 years ago
3.70 score 3 scripts 144 downloadsPPSFS - Partial Profile Score Feature Selection in High-Dimensional Generalized Linear Interaction Models
This is an implementation of the partial profile score feature selection (PPSFS) approach to generalized linear (interaction) models. The PPSFS is highly scalable even for ultra-high-dimensional feature space. See the paper by Xu, Luo and Chen (2021, <doi:10.4310/21-SII706>).
Last updated 3 years ago
2.70 score 1 stars 130 downloads