English

Optimal learning of high-dimensional classification problems using deep neural networks

Functional Analysis 2021-12-28 v2 Machine Learning Machine Learning

Abstract

We study the problem of learning classification functions from noiseless training samples, under the assumption that the decision boundary is of a certain regularity. We establish universal lower bounds for this estimation problem, for general classes of continuous decision boundaries. For the class of locally Barron-regular decision boundaries, we find that the optimal estimation rates are essentially independent of the underlying dimension and can be realized by empirical risk minimization methods over a suitable class of deep neural networks. These results are based on novel estimates of the L1L^1 and LL^\infty entropies of the class of Barron-regular functions.

Keywords

Cite

@article{arxiv.2112.12555,
  title  = {Optimal learning of high-dimensional classification problems using deep neural networks},
  author = {Philipp Petersen and Felix Voigtlaender},
  journal= {arXiv preprint arXiv:2112.12555},
  year   = {2021}
}
R2 v1 2026-06-24T08:29:37.988Z