L0Learn: A Scalable Package for Sparse Learning using L0 Regularization
Hussein Hazimeh, Rahul Mazumder, Tim Nonet; 24(205):1−8, 2023.
Abstract
This article introduces L0Learn, an open-source package designed for sparse linear regression and classification using L0 regularization. L0Learn offers scalable and approximate algorithms that are based on coordinate descent and local combinatorial optimization. The package is developed using C++ and features user-friendly interfaces for R and Python. It can effectively handle problems with millions of features, delivering competitive run times and statistical performance compared to state-of-the-art sparse learning packages. L0Learn is readily available on both CRAN and GitHub.
[abs]