Document worth reading: “A Survey of Tuning Parameter Selection for High-dimensional Regression”

Penalized (or regularized) regression, as represented by Lasso and its variants, has develop right into a typical technique for analyzing high-dimensional information when the amount of variables significantly exceeds the sample dimension. The effectivity of penalized regression relies upon crucially on the choice of the tuning parameter, which determines the amount of regularization and subsequently the sparsity stage of the fitted model. The optimum choice of tuning parameter is set by every the development of the design matrix and the unknown random error distribution (variance, tail conduct, and plenty of others). This article opinions the current literature of tuning parameter alternative for high-dimensional regression from every theoretical and smart views. We discuss different strategies that choose the tuning parameter to realize prediction accuracy or assist restoration. We moreover analysis a quantity of currently proposed methods for tuning-free high-dimensional regression. A Survey of Tuning Parameter Selection for High-dimensional Regression