On the Applicability of $p$-adic Numbers in Computational Modules for Neural Networks

The applicability of $p$-adic arithmetic as an intermediate computational module in an otherwise unchanged machine-learning pipeline is investigated. A one-feature linear regression on the scikit-learn Diabetes dataset serves as the test model. The fitted coefficients are represented in $\mathbb{Q}_p$, predictions are computed in that field, and rational reconstruction is applied to the outputs. In the pyAdic experiments, rational reconstruction either returns no result or produces values that differ from the baseline predictions; changing computational precision can change both the magnitude and sign of the reconstructed value. In SageMath, forward conversions succeed, but the reconstructed predictions differ from the baseline. An alternative representation based on digit reversal fails to preserve ordinary addition because of carry propagation. Under the tested settings, none of the test predictions is reconstructed correctly. These results show that the tested conversion and reconstruction procedures do not provide a compatible intermediate module even for linear regression. Models defined directly over $p$-adic data and operations offer a direction for further investigation.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20467
Primary Topic
p-Adic Analysis and Mathematical Physics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

On the Applicability of $p$-adic Numbers in Computational Modules for Neural Networks

Vladimir Evgrafov
arXiv (Cornell University)
p-Adic Analysis and Mathematical Physics
preprint

On the Applicability of $p$-adic Numbers in Computational Modules for Neural Networks

Vladimir Evgrafov
preprint en

Abstract

The applicability of $p$-adic arithmetic as an intermediate computational module in an otherwise unchanged machine-learning pipeline is investigated. A one-feature linear regression on the scikit-learn Diabetes dataset serves as the test model. The fitted coefficients are represented in $\mathbb{Q}_p$, predictions are computed in that field, and rational reconstruction is applied to the outputs. In the pyAdic experiments, rational reconstruction either returns no result or produces values that differ from the baseline predictions; changing computational precision can change both the magnitude and sign of the reconstructed value. In SageMath, forward conversions succeed, but the reconstructed predictions differ from the baseline. An alternative representation based on digit reversal fails to preserve ordinary addition because of carry propagation. Under the tested settings, none of the test predictions is reconstructed correctly. These results show that the tested conversion and reconstruction procedures do not provide a compatible intermediate module even for linear regression. Models defined directly over $p$-adic data and operations offer a direction for further investigation.

arXiv (Cornell University)
p-Adic Analysis and Mathematical Physics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon