Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bieri, Joanna, Costa, Edgar, Deines, Alyson, Lee, Kyu-Hwan, Lowry-Duda, David, Oliver, Thomas, Qi, Yidi, Veenstra, Tamara
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917351607238656
author Bieri, Joanna
Costa, Edgar
Deines, Alyson
Lee, Kyu-Hwan
Lowry-Duda, David
Oliver, Thomas
Qi, Yidi
Veenstra, Tamara
author_facet Bieri, Joanna
Costa, Edgar
Deines, Alyson
Lee, Kyu-Hwan
Lowry-Duda, David
Oliver, Thomas
Qi, Yidi
Veenstra, Tamara
contents We apply one-dimensional convolutional neural networks to the Frobenius traces of elliptic curves over $\mathbb{Q}$ and evaluate and interpret their predictive capacity. In keeping with similar experiments by Kazalicki--Vlah, Bujanović--Kazalicki--Novak, and Pozdnyakov, we observe high accuracy predictions for the analytic rank across a range of conductors. We interpret the prediction using saliency curves and explore the interesting interplay between murmurations and Mestre--Nagao sums, the details of which vary with the conductor and the (predicted) rank.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17681
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves
Bieri, Joanna
Costa, Edgar
Deines, Alyson
Lee, Kyu-Hwan
Lowry-Duda, David
Oliver, Thomas
Qi, Yidi
Veenstra, Tamara
Number Theory
Machine Learning
We apply one-dimensional convolutional neural networks to the Frobenius traces of elliptic curves over $\mathbb{Q}$ and evaluate and interpret their predictive capacity. In keeping with similar experiments by Kazalicki--Vlah, Bujanović--Kazalicki--Novak, and Pozdnyakov, we observe high accuracy predictions for the analytic rank across a range of conductors. We interpret the prediction using saliency curves and explore the interesting interplay between murmurations and Mestre--Nagao sums, the details of which vary with the conductor and the (predicted) rank.
title Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves
topic Number Theory
Machine Learning
url https://arxiv.org/abs/2603.17681