Indefinite Kernel Network with lq-Norm Regularization

Abstract EN

We study the asymptotical properties of indefinite kernel network with lq-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 space X and Lτ condition for the probability measure ρX, satisfied error bounds and learning rates are deduced.