arXiv · 2603.17681
Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves
Abstract
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, Bujanovi\'{c}--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.
Explore related subjects
Keep this discovery
Joanna Bieri, Edgar Costa, Alyson Deines, Kyu-Hwan Lee, David Lowry-Duda, Thomas Oliver, Yidi Qi, Tamara Veenstra. 2026-03-18. Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves. https://arxiv.org/abs/2603.17681
Cite the original work for its findings. Save a collection to share your selection of sources.