English

Convergence bounds for local least squares approximation

Numerical Analysis 2023-01-24 v2 Numerical Analysis Machine Learning

Abstract

We consider the problem of approximating a function in a general nonlinear subset of L2L^2, when only a weighted Monte Carlo estimate of the L2L^2-norm can be computed. Of particular interest in this setting is the concept of sample complexity, the number of sample points that are necessary to achieve a prescribed error with high probability. Reasonable worst-case bounds for this quantity exist only for particular model classes, like linear spaces or sets of sparse vectors. For more general sets, like tensor networks or neural networks, the currently existing bounds are very pessimistic. By restricting the model class to a neighbourhood of the best approximation, we can derive improved worst-case bounds for the sample complexity. When the considered neighbourhood is a manifold with positive local reach, its sample complexity can be estimated by means of the sample complexities of the tangent and normal spaces and the manifold's curvature.

Keywords

Cite

@article{arxiv.2208.10954,
  title  = {Convergence bounds for local least squares approximation},
  author = {Philipp Trunschke},
  journal= {arXiv preprint arXiv:2208.10954},
  year   = {2023}
}

Comments

17 pages, 4 figures, text overlap with arXiv:2108.05237

R2 v1 2026-06-25T01:54:12.650Z