Ridge Kernel Averaging and Uniform Approximation
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911119416754176 |
|---|---|
| author | Tian, James |
| author_facet | Tian, James |
| contents | We develop a framework for function classes generated by parametric ridge kernels: one-dimensional kernels composed with affine projections and averaged over a parameter measure. The induced kernels are positive definite, and the resulting integral class coincides isometrically with its reproducing kernel Hilbert space. We characterize all kernels obtainable by varying the measure as the uniform closure of the conic hull of ridge atoms, giving a sharp universality criterion; a slice-wise polynomial versus non-polynomial dichotomy governs expressivity. We then analyze random-kernel networks whose activations may be indefinite but have a positive-definite mean. For these networks we prove a Monte Carlo rate with mean-squared error of order one over $N$ and a high-probability uniform bound on compact sets, without requiring pathwise positive definiteness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17410 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ridge Kernel Averaging and Uniform Approximation Tian, James Functional Analysis Primary 41A30. Secondary 41A25, 41A30, 46E22, 60E15, 68T07 We develop a framework for function classes generated by parametric ridge kernels: one-dimensional kernels composed with affine projections and averaged over a parameter measure. The induced kernels are positive definite, and the resulting integral class coincides isometrically with its reproducing kernel Hilbert space. We characterize all kernels obtainable by varying the measure as the uniform closure of the conic hull of ridge atoms, giving a sharp universality criterion; a slice-wise polynomial versus non-polynomial dichotomy governs expressivity. We then analyze random-kernel networks whose activations may be indefinite but have a positive-definite mean. For these networks we prove a Monte Carlo rate with mean-squared error of order one over $N$ and a high-probability uniform bound on compact sets, without requiring pathwise positive definiteness. |
| title | Ridge Kernel Averaging and Uniform Approximation |
| topic | Functional Analysis Primary 41A30. Secondary 41A25, 41A30, 46E22, 60E15, 68T07 |
| url | https://arxiv.org/abs/2508.17410 |