Feature screening for ultrahigh-dimensional classification via Gini distance correlation
Document Type
Lecture
Publication Date
3-23-2023
Abstract
Gini distance correlation (GDC) was recently proposed to measure dependence between a categorical variable and numerical random vector. In this talk, we utilize the GDC to establish a feature screening for ultrahigh-dimensional classification where the response variable is categorical. It can be used for screening individual features as well as grouped features. The proposed procedure possesses several appealing properties. It is model-free. No model specification is needed. It holds the sure independence screening property and the ranking consistency property. The proposed screening method can deal with the case that the response has divergent number of categories. Simulation and real data applications are presented to compare performance of the proposed screening procedure.
Relational Format
presentation
Recommended Citation
Dang, Xin, "Feature screening for ultrahigh-dimensional classification via Gini distance correlation" (2023). Probability & Statistics Seminar. 19.
https://egrove.olemiss.edu/math_statistics/19
