English

Convergence for adaptive resampling of random Fourier features

Numerical Analysis 2026-05-19 v2 Numerical Analysis Machine Learning

Abstract

The machine learning random Fourier feature method for data in high dimension is computationally and theoretically attractive since the optimization is based on a convex standard least squares problem and independent sampling of Fourier frequencies. The challenge is to sample the Fourier frequencies well. This work proves convergence of a data adaptive method based on resampling the frequencies asymptotically optimally, as the number of nodes and amount of data tend to infinity. Numerical results based on resampling and adaptive random walk steps together with approximations of the least squares problem by conjugate gradient iterations confirm the analysis for regression and classification problems.

Keywords

Cite

@article{arxiv.2509.03151,
  title  = {Convergence for adaptive resampling of random Fourier features},
  author = {Xin Huang and Aku Kammonen and Anamika Pandey and Mattias Sandberg and Erik von Schwerin and Anders Szepessy and Raúl Tempone},
  journal= {arXiv preprint arXiv:2509.03151},
  year   = {2026}
}

Comments

50 pages, 19 figures