English

The minimal width of universal $p$-adic ReLU neural networks

Number Theory 2026-03-03 v1 Machine Learning

Abstract

We determine the minimal width of pp-adic neural networks with the universal approximation property for continuous Qp\mathbb Q_p-valued functions on compact open subsets with respect to the LqL_q norms and the C1C_1 norm, where the activation function is a natural pp-adic analogue of the ReLU function.

Keywords

Cite

@article{arxiv.2603.00064,
  title  = {The minimal width of universal $p$-adic ReLU neural networks},
  author = {Sándor Z. Kiss and Ambrus Pál},
  journal= {arXiv preprint arXiv:2603.00064},
  year   = {2026}
}

Comments

16 pages, comments welcome!