“…Sparse learning models with the ℓ 1 norm, such as ℓ 1 Support vector machine (SVM) classification [38,51,55] and ℓ 1 SVM regression [7,37,55], have received increasing attention in machine learning. Motivated by the need of sparse learning algorithms, the notion of reproducing kernel Banach spaces (RKBSs) was introduced in [76] and further developed in [40,56,57,72]. RKBSs with the ℓ 1 norm [40,56,57] have been proven successful in promoting sparsity in representations for learned functions.…”