A Class of Random-Kernel Network Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 17 references that are in the map. First posted on arXiv 1 Sep 2025.
Builds on
7 of 17 references.
References · 7
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
- 2015Deep Kernel Learningcited by 445
- 2019The generalization error of random features regression: Precise asymptotics and double descent curvecited by 413
- 2016Benefits of depth in neural networkscited by 250
- 2015The Power of Depth for Feedforward Neural Networkscited by 183
- 2016Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivitycited by 138
- 2016Learning Scalable Deep Kernels with Recurrent Structurecited by 22
Built on by
Not cited yet.