math.NTFeb 10, 2026

The minimal width of universal pp-adic ReLU neural networks

Authors: Sándor Z. Kiss, Ambrus Pál

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.

Explore similar work

Mar 31, 2026

pp-adic Character Neural Network

We propose a new frame work of pp-adic neural network. Unlike the original pp-adic neural network by S.\ Albeverio, A.\ Khrennikov, and B.\ Tirrozi using a family of characteristic functions indexed by hyperparameters of precision as activation functions, we use a single injective pp-adic character on the topological Abelian group Zp\mathbb{Z}_p of pp-adic integers as an activation function. We prove the pp-adic universal approximation theorem for this formulation of pp-adic neural network, and reduce it to the feasibility problem of polynomial equations over the finite ring of integers modulo a power of pp.
Oct 14, 2026

The minimal width of neural networks and immersions of real projective space

We investigate the minimal width of deep neural networks that can approximate all continuous functions from Rn\mathbb{R}^n to Rm\mathbb{R}^m in the topology of uniform convergence on compact subsets. We show that whenever the real projective space RPn−1\mathbb{RP}^{n-1} admits a smooth immersion into Rn\mathbb{R}^n, the minimal width is at least n+min⁡{n,m}n+\min\{n,m\}, assuming that the activation function is continuous and monotone. As a consequence, the minimal width of ReLU networks is n+mn+m whenever nn is equal to 2, 3, 4, 7 or 8 and 1≤m≤n1\le m \le n, extending results of Hanin-Sellke and Hwang.
Jul 6, 2026

Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One

In this paper, we study the universal approximation property of residual neural networks, and obtain some new results. For input and output dimensions dxd_x and dyd_y, and LeakyReLU, ReLU, ReLU-like activation functions, the upper and lower bounds of the minimum block width are established. To achieve LpL^p approximation (1≤p<+∞)(1\leq p <+\infty) on any compact domain, we show that the exact minimum block width is max⁡{dx,dy}\max\{d_x,d_y\} when each residual branch has inner width 1. Furthermore, we show that residual neural networks with block width min⁡{dx+dy,max⁡{2dx+1,dy}}\min\{d_x+d_y, \max\{2d_x+1,d_y\}\} can achieve uniform approximation on any compact domain under the constraint that each residual branch has inner width 1. Besides, for any activation function family, we prove that there exist functions that cannot be approximated by residual neural networks with block width less than max⁡{dx,dy}\max\{d_x, d_y\}, both in the LpL^p sense and the uniform sense, regardless of inner width.