On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions
This work addresses foundational issues in RKBS theory for researchers in machine learning and functional analysis, offering a unified approach to constructions and definitions.
The paper tackles the lack of a unified definition and framework for reproducing kernel Banach spaces (RKBS), proposing a generic definition independent of construction and a framework that unifies existing constructions via continuous bilinear forms and feature maps, including a new class of Orlicz RKBSs and representer theorems for machine learning.
Recently, there has been emerging interest in constructing reproducing kernel Banach spaces (RKBS) for applied and theoretical purposes such as machine learning, sampling reconstruction, sparse approximation and functional analysis. Existing constructions include the reflexive RKBS via a bilinear form, the semi-inner-product RKBS, the RKBS with $\ell^1$ norm, the $p$-norm RKBS via generalized Mercer kernels, etc. The definitions of RKBS and the associated reproducing kernel in those references are dependent on the construction. Moreover, relations among those constructions are unclear. We explore a generic definition of RKBS and the reproducing kernel for RKBS that is independent of construction. Furthermore, we propose a framework of constructing RKBSs that unifies existing constructions mentioned above via a continuous bilinear form and a pair of feature maps. A new class of Orlicz RKBSs is proposed. Finally, we develop representer theorems for machine learning in RKBSs constructed in our framework, which also unifies representer theorems in existing RKBSs.