The Group Lasso for Design of Experiments
This work addresses experimental design for statisticians and researchers, but it is incremental as it adapts an existing method to a new application.
The paper tackles the problem of constructing optimal design matrices for experiments by applying the group lasso, transforming it into a group lasso problem, and shows in numerical examples that orthogonal arrays can be obtained as solutions.
We introduce an application of the group lasso to design of experiments. Note that we are NOT trying to explain experimental design for the group lasso. Conversely, we explain how we can use the idea of the group lasso in experimental design, showing that the problem of constructing an optimal design matrix can be transformed into a problem of the group lasso. In some numerical examples, we show that we can obtain the orthogonal arrays as the solutions of the group lasso problems.