Results 101 to 110 of about 13,358 (271)

Application of Reproducing Kernel Hilbert Space Method for Solving a Class of Nonlinear Integral Equations

open access: yes, 2017
A new approach based on the Reproducing Kernel Hilbert Space Method is proposed to approximate the solution of the second-kind nonlinear integral equations.
Sedigheh Farzaneh Javan   +2 more
semanticscholar   +1 more source

Radial kernels and their reproducing kernel Hilbert spaces

open access: yesJournal of Complexity, 2010
Let \(R\) be a continuous convex function on a Hilbert space \(H\). In learning theory, \[ A(\lambda):= \inf_{h\in H} \{\lambda\| h\|^2+ R(h)\}- \inf_{h\in H} R(h) \] is called an approximation error function. Here, \(H\) is a reproducing kernel Hilbert space (RKHS) of functions on \(\mathbb{R}^d\), i.e., such that the evaluations \(\delta_x: h\mapsto ...
Scovel, Clint   +3 more
openaire   +1 more source

A Characterization for reproducing kernel Hilbert spaces

open access: yesJournal of Mathematical Analysis and Applications, 1974
AbstractLet G(t, s) be the Green's functions associated with N, a differential operator restricted to certain boundary conditions. Define (u, v)N = (Nu, v)L2. It is shown that the reproducing kernel Hilbert space generated by G is the same as the Hilbert-space completion with respect to ∥ · ∥N of the set of real valued functions which are in C2n and ...
openaire   +2 more sources

Flexible Expectile Regression in Reproducing Kernel Hilbert Spaces

open access: yesTechnometrics, 2017
Expectile, first introduced by Newey and Powell in 1987 in the econometrics literature, has recently become increasingly popular in risk management and capital allocation for financial institutions due to its desirable properties such as coherence and elicitability.
Yang, Yi, Zhang, Teng, Zou, Hui
openaire   +3 more sources

Learning Rate of Regularized Regression Associated with Zonal Translation Networks

open access: yesMathematics
We give a systematic investigation on the reproducing property of the zonal translation network and apply this property to kernel regularized regression.
Xuexue Ran, Baohuai Sheng, Shuhua Wang
doaj   +1 more source

Some Lemmas on Reproducing Kernel Hilbert Spaces [PDF]

open access: yes, 2002
Reproducing kernel Hilbert spaces (RKHS) provides a framework for approximation from finite data using the idea of bounded linear functionals. The approximation problem in this case can be viewed as the inverse problem of finding the optimum operator from the Euclidean space of observations to some subspace of the RKHS.
Dodd, T.J., Harrison, R.F.
openaire  

Home - About - Disclaimer - Privacy