REVIEW 3 cited by
Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
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 $\mathbb{R}^d$.
Forward citations
Cited by 3 Pith papers
-
The Cost of Discretization in Functional Linear Regression: Minimax Rates and Adaptation
Matching minimax prediction rates for discretely observed functional linear regression are n^{-ν/(ν+1)}+(nm)^{-ν/κ} under independent design, and those two terms plus m^{-ν}+m^{-4α} under common design.
-
Deep Ritz method with Fourier feature mapping: A deep learning approach for solving variational models of microstructure
Adding Fourier features to the input layer lets the Deep Ritz Method generate high-frequency solutions for non-convex multi-well energy problems, while increasing network depth alone does not consistently do so.
-
Optimal Convergence Rates for Neural Operators
Two-layer neural operators trained with early-stopped gradient descent achieve the same minimax convergence rates as kernel methods in the neural tangent kernel regime.
Discussion (0). Continue with ORCID to comment.