Ultra-High Dimensionality: A Challenge in Variable Selection and

In the era of big data, the high dimensionality in covariates poses unprecedented challenges in variable selection and classification problems. In this paper, we suggest an efficient method for simultaneous classification and identifying important variables in the setting of ultra-high dimensional models. The implementation of the suggested method is not limited by the dimensionality of the models and requires much less computation. Numerical examples and a real data analysis are used to demonstrate its finite sample performance.