2005 ◽  
Vol 2005 (17) ◽  
pp. 2757-2768 ◽  
Author(s):  
E. Jebbari ◽  
F. Soltani

We use reproducing kernel Hilbert spaces to give the best approximation for Laguerre-type Weierstrass transform. Estimates of extremal functions are also discussed.


2013 ◽  
Vol 11 (05) ◽  
pp. 1350020 ◽  
Author(s):  
HONGWEI SUN ◽  
QIANG WU

We study the asymptotical properties of indefinite kernel network with coefficient regularization and dependent sampling. The framework under investigation is different from classical kernel learning. Positive definiteness is not required by the kernel function and the samples are allowed to be weakly dependent with the dependence measured by a strong mixing condition. By a new kernel decomposition technique introduced in [27], two reproducing kernel Hilbert spaces and their associated kernel integral operators are used to characterize the properties and learnability of the hypothesis function class. Capacity independent error bounds and learning rates are deduced.


2014 ◽  
Vol 9 (4) ◽  
pp. 827-931 ◽  
Author(s):  
Joseph A. Ball ◽  
Dmitry S. Kaliuzhnyi-Verbovetskyi ◽  
Cora Sadosky ◽  
Victor Vinnikov

2009 ◽  
Vol 80 (3) ◽  
pp. 430-453 ◽  
Author(s):  
JOSEF DICK

AbstractWe give upper bounds on the Walsh coefficients of functions for which the derivative of order at least one has bounded variation of fractional order. Further, we also consider the Walsh coefficients of functions in periodic and nonperiodic reproducing kernel Hilbert spaces. A lower bound which shows that our results are best possible is also shown.


2017 ◽  
Vol 87 (2) ◽  
pp. 225-244 ◽  
Author(s):  
Rani Kumari ◽  
Jaydeb Sarkar ◽  
Srijan Sarkar ◽  
Dan Timotin

Sign in / Sign up

Export Citation Format

Share Document