Reproducing Kernel Banach Spaces with the l1 Norm

Abstract

Targeting at sparse learning, we construct Banach spaces B of functions on an input space X with the properties that (1) B possesses an l1 norm in the sense that it is isometrically isomorphic to the Banach space of integrable functions on X with respect to the counting measure; (2) point evaluations are continuous linear functionals on B and are representable through a bilinear form with a kernel function; (3) regularized learning schemes on B satisfy the linear representer theorem. Examples of kernel functions admissible for the construction of such spaces are given.

28 pages, an extra section was added

References in corpus (1)

• Kernel Approximation on Manifolds I: Bounding the Lebesgue Constant

Cited by in corpus (13)

• Solving Support Vector Machines in Reproducing Kernel Banach Spaces with Positive Definite Functions
• Global Variational Method for Fingerprint Segmentation by Three-part Decomposition
• On the Definiteness of Earth Mover's Distance and Its Relation to Set Intersection
• Parameter Choices for Sparse Regularization with the ${\ell }_1$ Norm
• Representer Theorems in Banach Spaces: Minimum Norm Interpolation, Regularized Learning and Semi-Discrete Inverse Problems
• Does generalization performance of $l^q$ regularization learning depend on $q$? A negative example
• Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
• Multi-task Learning in Vector-valued Reproducing Kernel Banach Spaces with the ${\ell }^1$ Norm
• Operator Reproducing Kernel Hilbert Spaces
• Learning rates of $l^q$ coefficient regularization learning with Gaussian kernel
• Universalities of Reproducing Kernels Revisited
• On multipliers of reproducing kernel Banach and Hilbert spaces
• Vector-valued Reproducing Kernel Banach Spaces with Group Lasso Norms