Score: 0

A Class of Random-Kernel Network Models

Published: September 1, 2025 | arXiv ID: 2509.01090v1

By: James Tian

Potential Business Impact:

Makes computers learn faster with less guessing.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

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.

Page Count
16 pages

Category
Computer Science:
Machine Learning (CS)