math.NTMar 31, 2026

pp-adic Character Neural Network

Authors: Tomoki Mihara

Abstract

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.

Explore similar work

CardsList
  1. Expressivity of Shallow Neural Networks Over Finite Fields

    Jul 19, 2026Maksym Zubkov, Carol Wu, Shiwei Yang +2Shallow Neural NetworksPolynomial Neural Networks

  2. Efficient Approximation to Analytic and LpL^p functions by Height-Augmented ReLU Networks

    Mar 11, 2026ZeYu Li, FengLei Fan, TieYong ZengNeural Network Approximation TheoryReLU Neural Networks

  3. Continuous Optimization for p-adic Models

    Sep 21, 2026Julian Salazar, Dimitri Kanevsky, Matt Harvey +2Gradient Descent