Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

09/22/2020
by   Lin Chen, et al.
13

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 𝕊^d-1. Additionally, we prove that the exponential power kernel with a smaller power (making the kernel more non-smooth) leads to a larger RKHS, when it is restricted to the sphere 𝕊^d-1 and when it is defined on the entire ℝ^d.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/03/2020

On the Similarity between the Laplace and Neural Tangent Kernels

Recent theoretical work has shown that massively overparameterized neura...
research
03/02/2020

A Fractional Hawkes process

We modify ETAS models by replacing the Pareto-like kernel proposed by Og...
research
10/04/2021

Generalized Kernel Thinning

The kernel thinning (KT) algorithm of Dwivedi and Mackey (2021) compress...
research
03/12/2018

Poisson Kernel-Based Clustering on the Sphere: Convergence Properties, Identifiability, and a Method of Sampling

Many applications of interest involve data that can be analyzed as unit ...
research
04/07/2021

Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks

Deep residual network architectures have been shown to achieve superior ...
research
05/19/2022

Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel

Recent research in the theory of overparametrized learning has sought to...
research
02/03/2020

Stochastic geometry to generalize the Mondrian Process

The Mondrian process is a stochastic process that produces a recursive p...

Please sign up or login with your details

Forgot password? Click here to reset