Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

Abstract

We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricted to the sphere $\mathbb{S}^{d-1}$. Additionally, we prove that the exponential power kernel with a smaller power (making the kernel less smooth) leads to a larger RKHS, when it is restricted to the sphere $\mathbb{S}^{d-1}$ and when it is defined on the entire $\mathbb{R}^d$.

Cite

Text

Chen and Xu. "Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS." International Conference on Learning Representations, 2021.

Markdown

[Chen and Xu. "Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/chen2021iclr-deep/)

BibTeX

@inproceedings{chen2021iclr-deep,
  title     = {{Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS}},
  author    = {Chen, Lin and Xu, Sheng},
  booktitle = {International Conference on Learning Representations},
  year      = {2021},
  url       = {https://mlanthology.org/iclr/2021/chen2021iclr-deep/}
}