English

Approximation power of random neural networks

Machine Learning 2019-10-21 v2 Machine Learning

Abstract

This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding infinite width networks; (c) finite width networks obtained by starting with standard Gaussian initialization, and then adding a vanishingly small correction to the weights. The primary result is a fully quantified bound on the rate of approximation of general general continuous functions: in all three cases, a function ff can be approximated with complexity f1(d/δ)O(d)\|f\|_1 (d/\delta)^{\mathcal{O}(d)}, where δ\delta depends on continuity properties of ff and the complexity measure depends on the weight magnitudes and/or cardinalities. Along the way, a variety of ancillary results are developed: an exact construction of Gaussian densities with infinite width networks, an elementary stand-alone proof scheme for approximation via convolutions of radial basis functions, subsampling rates for infinite width networks, and depth separation for corrected networks.

Keywords

Cite

@article{arxiv.1906.07709,
  title  = {Approximation power of random neural networks},
  author = {Bolton Bailey and Ziwei Ji and Matus Telgarsky and Ruicheng Xian},
  journal= {arXiv preprint arXiv:1906.07709},
  year   = {2019}
}

Comments

This submission constitutes a poor approach to the problem, and has no scientific purpose. A superior (different) approach (and stronger final result, also treating the NTK) has appeared in arXiv:1910.06956 ; please see that work instead

R2 v1 2026-06-23T09:57:11.481Z