A Class of Random-Kernel Network Models
Machine Learning
2025-09-03 v1 Numerical Analysis
Functional Analysis
Numerical Analysis
Abstract
We introduce random-kernel networks, a multilayer extension of random feature models where depth is created by deterministic kernel composition and randomness enters only in the outermost layer. We prove that deeper constructions can approximate certain functions with fewer Monte Carlo samples than any shallow counterpart, establishing a depth separation theorem in sample complexity.
Cite
@article{arxiv.2509.01090,
title = {A Class of Random-Kernel Network Models},
author = {James Tian},
journal= {arXiv preprint arXiv:2509.01090},
year = {2025}
}