arXiv Open Access 2022

Limitations on approximation by deep and shallow neural networks

Guergana Petrova Przemysław Wojtaszczyk

Lihat Sumber

Abstrak

We prove Carl's type inequalities for the error of approximation of compact sets K by deep and shallow neural networks. This in turn gives lower bounds on how well we can approximate the functions in K when requiring the approximants to come from outputs of such networks. Our results are obtained as a byproduct of the study of the recently introduced Lipschitz widths.

Topik & Kata Kunci

stat.ML cs.LG math.FA

Penulis (2)

Guergana Petrova

Przemysław Wojtaszczyk

Format Sitasi

APA MLA BibTeX

Petrova, G., Wojtaszczyk, P. (2022). Limitations on approximation by deep and shallow neural networks. https://arxiv.org/abs/2212.02223

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓