Learning a Sparse Representation of Barron Functions with the Inverse Scale Space Flow

Authors

  • Tjeerd Jan Heeringa
  • Tim Roith
  • Christoph Brune
  • Martin Burger

DOI:

https://doi.org/10.4208/jml.240123

Keywords:

Barron Space, Bregman Iterations, Sparse Neural Networks, Inverse Scale Space, Optimization.

Abstract

This paper presents a method for finding a sparse representation of Barron functions. Specifically, given an $L^2$ function $f,$ the inverse scale space flow is used to find a sparse measure $\mu$ minimising the $L^2$ loss between the Barron function associated to the measure $\mu$ and the function $f.$ The convergence properties of this method are analysed in an ideal setting and in the cases of measurement noise and sampling bias. In an ideal setting the objective decreases strictly monotone in time to a minimizer with $\mathcal{O}(1/t),$ and in the case of measurement noise or sampling bias the optimum is achieved up to a multiplicative or additive constant. This convergence is preserved on discretization of the parameter space, and the minimizers on increasingly fine discretizations converge to the optimum on the full parameter space.

Published

2025-03-12

Issue

Section

Articles