Regularized learning in Banach spaces as an optimization problem: representer theorems

DOI10.1007/s10898-010-9575-zzbMath1281.90088OpenAlexW2099720998MaRDI QIDQ693135

Jun Zhang, Haizhang Zhang

Publication date: 7 December 2012

Published in: Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10898-010-9575-z

zbMATH Keywords

semi-inner productsreproducing kernel Banach spacesregularization networksrepresenter theoremssupport vector machine classification

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Programming in abstract spaces (90C48) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Related Items

Convex optimization in sums of Banach spaces ⋮ Functional reproducing kernel Hilbert spaces for non-point-evaluation functional data ⋮ On reproducing kernel Banach spaces: generic definitions and unified framework of constructions ⋮ Support Vector Machines in Reproducing Kernel Hilbert Spaces Versus Banach Spaces ⋮ Regularized learning schemes in feature Banach spaces ⋮ Sparse machine learning in Banach spaces ⋮ On the K-functional in learning theory ⋮ When is there a representer theorem? Nondifferentiable regularisers and Banach spaces ⋮ Separability of reproducing kernel spaces ⋮ Generalized Mercer Kernels and Reproducing Kernel Banach Spaces ⋮ Solving support vector machines in reproducing kernel Banach spaces with positive definite functions ⋮ On Lipschitz implicit function theorems in Banach spaces and applications ⋮ A unifying representer theorem for inverse problems and machine learning ⋮ Unnamed Item ⋮ Multi-task learning in vector-valued reproducing kernel Banach spaces with the \(\ell^1\) norm ⋮ When is there a representer theorem? Reflexive Banach spaces ⋮ Generalized support vector regression: Duality and tensor-kernel representation ⋮ Ontology computation for graph spaces focus on partial vertex pairs ⋮ The learning rates of regularized regression based on reproducing kernel Banach spaces ⋮ Multikernel Regression with Sparsity Constraint ⋮ Generalized representer theorems in Banach spaces ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On-line learning of smooth functions of a single variable
• Some examples for solving systems of algebraic equations by calculating Gröbner bases
• Regularization networks and support vector machines
• Feature space perspectives for learning the kernel
• Some results on Tchebycheffian spline functions and stochastic processes
• Maximal margin classification for metric spaces
• Generalized semi-inner products with applications to regularized learning
• Asymptotic analysis of penalized likelihood and related estimators
• On the mathematical foundations of learning
• 10.1162/15324430260185600
• Semi-Inner-Product Spaces
• Just relax: convex programming methods for identifying sparse signals in noise
• An Introduction to Banach Space Theory
• Learning Theory
• On the localization and directionalization of uniform convexity
• Classes of Semi-Inner-Product Spaces
• Theory of Reproducing Kernels
• Functional analysis and infinite-dimensional geometry
• On the dual formulation of regularized linear systems with convex risks