On the speed of uniform convergence in Mercer's theorem
Not on the map. Why?
Abstract (arXiv)
The classical Mercer's theorem claims that a continuous positive definite kernel K(mathbf x, mathbf y) on a compact set can be represented as sumi=1^∞ λiφi(mathbf x)φi(mathbf y) where (λi,φi) are eigenvalue-eigenvector pairs of the corresponding integral operator. This infinite representation is known to converge uniformly to the kernel K. We estimate the speed of this convergence in terms of the decay rate of eigenvalues and demonstrate that for 2m times differentiable kernels the first N terms of the series approximate K as Obig((sumi=N+1^∞λi)^fracmm+nbig) or Obig((sumi=N+1^∞λ2i)^fracm2m+nbig). Finally, we demonstrate some applications of our results to a spectral charaterization of integral operators with continuous roots and other powers.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 1 of its 17 references that are in the map. First posted on arXiv 1 May 2022.
Builds on
1 of 17 references.
References · 1
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 3.
5 papers.
- 2026On the Intrinsic Dimensions of Data in Kernel Learningcited by 1
- 2024Gaussian kernel expansion with basis functions uniformly bounded in L∞cited by 0
- 2025Adaptive prediction theory combining offline and online learningcited by 0
- 2026Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximationcited by 0
- 2026Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholdingcited by 0
- 2026Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding25 May 2026
- 2026Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation27 Apr 2026
- 2026On the Intrinsic Dimensions of Data in Kernel Learning22 Jan 2026
- 2025Adaptive prediction theory combining offline and online learning29 Nov 2025
- 2024Gaussian kernel expansion with basis functions uniformly bounded in L∞2 Oct 2024