Indefinite Kernel Network withlq-Norm Regularization
Keyword(s):
We study the asymptotical properties of indefinite kernel network withlq-norm regularization. The framework under investigation is different from classical kernel learning. Positive semidefiniteness is not required by the kernel function. By a new step stone technique, without any interior cone condition for input spaceXandLτcondition for the probability measureρX, satisfied error bounds and learning rates are deduced.
2013 ◽
Vol 11
(05)
◽
pp. 1350020
◽
2012 ◽
Vol 10
(05)
◽
pp. 1250043
◽
Keyword(s):
Keyword(s):
Keyword(s):