Learning a Sparse Representation of Barron Functions with the Inverse Scale Space Flow
Year: 2025
Author: Tjeerd Jan Heeringa, Tim Roith, Christoph Brune, Martin Burger
Journal of Machine Learning, Vol. 4 (2025), Iss. 1 : pp. 48–88
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.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/jml.240123
Journal of Machine Learning, Vol. 4 (2025), Iss. 1 : pp. 48–88
Published online: 2025-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 41
Keywords: Barron Space Bregman Iterations Sparse Neural Networks Inverse Scale Space Optimization.
Author Details
Tjeerd Jan Heeringa Email
Tim Roith Email
Christoph Brune Email
Martin Burger Email