Regularization networks with indefinite kernels

DOI10.1016/j.jat.2012.10.001zbMath1295.68141MaRDI QIDQ1935751

Qiang Wu

Publication date: 19 February 2013

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jat.2012.10.001

zbMATH Keywords

learning theory; reproducing kernel Hilbert space; coefficient-based regularization; indefinite kernel; least square regression; learning rates; capacity independent error bound

Mathematics Subject Classification ID

68Q32: Computational learning theory

62J02: General nonlinear regression

68T05: Learning and adaptive systems in artificial intelligence

46E22: Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces)

Related Items

Bias corrected regularization kernel method in ranking, Nyström subsampling method for coefficient-based regularized regression, Distributed learning with indefinite kernels, Guaranteed Classification via Regularized Similarity Learning, Coefficient-based regression with non-identical unbounded sampling, Optimal rates for coefficient-based regularized regression, Indefinite kernels in least squares support vector machines and principal component analysis, Kernel-based sparse regression with the correntropy-induced loss, INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING, Regression learning with non-identically and non-independently sampling, A new realization of rational functions, with applications to linear combination interpolation, the Cuntz relations and kernel decompositions