On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains

In this paper, we provide a strategy to determine the eigenvalue decay rate (EDR) of a large class of kernel functions defined on a general domain rather than $\mathbb{S}^{d}$. This class of kernel functions include but are not limited to the neural tangent kernel associated with neural networks with different depths and various activation functions. After proving that the dynamics of training the wide neural networks uniformly approximated that of the neural tangent kernel regression on general domains, we can …

class domain domains eigenvalue functions general kernel network paper rate strategy