ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2312.02671
21
0

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

5 December 2023
T. J. Heeringa
Tim Roith
Christoph Brune
Martin Burger
ArXivPDFHTML
Abstract

This paper presents a method for finding a sparse representation of Barron functions. Specifically, given an L2L^2L2 function fff, the inverse scale space flow is used to find a sparse measure μ\muμ minimising the L2L^2L2 loss between the Barron function associated to the measure μ\muμ and the function fff. 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 O(1/t)\mathcal{O}(1/t)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.

View on arXiv
Comments on this paper