TIKHONOV OR LASSO REGULARIZATION: WHICH IS BETTER AND WHEN. IN TOOLS WITH ARTIFICIAL INTELLIGENCE

pages 795–802. IEEE, 2013. It is well known that supervised learning problems with ℓ1 (Lasso) and ℓ2 (Tikhonov or Ridge) regularizers will result in very different solutions. For example, the ℓ1 solution vector will be sparser and can potentially be used both for prediction and feature selection. However, given a data set it is often hard to determine