A multiobjective continuation method to compute the regularization path of deep neural networks

arXiv:2308.12044v5 Announce Type: replace
Abstract: Sparsity is a highly desired feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models (due to the smaller number of relevant features), and robustness. For linear models, it is well known that there exists a \emph{regularization path} connecting the sparsest solution in terms of the $\ell^1$ norm, i.e., zero weights and the non-regularized solution. Very recently, there was a first attempt to extend the concept of regularization paths …

abstract arxiv compute cs.ai cs.lg efficiency feature features interpretability linear math.oc networks neural networks numerical path regularization robustness sparsity stat.ml type