Efficient Experimental Design for Regularized Linear Models

TL;DR

This paper introduces an experimental design method using nearly orthogonal Latin hypercube designs to improve variable selection accuracy in regularized linear models like Lasso.

Contribution

It proposes a systematic approach for constructing nearly orthogonal Latin hypercube designs to enhance data collection for regularized linear models.

Findings

Improved variable selection accuracy demonstrated in examples

Systematic construction methods for the designs

Enhanced model performance with the proposed design approach

Abstract

Regularized linear models, such as Lasso, have attracted great attention in statistical learning and data science. However, there is sporadic work on constructing efficient data collection for regularized linear models. In this work, we propose an experimental design approach, using nearly orthogonal Latin hypercube designs, to enhance the variable selection accuracy of the regularized linear models. Systematic methods for constructing such designs are presented. The effectiveness of the proposed method is illustrated with several examples.