Machine Learning meets Number Theory: The Data Science of Birch-Swinnerton-Dyer

Abstract

Empirical analysis is often the first step towards the birth of a conjecture. This is the case of the Birch-Swinnerton-Dyer (BSD) Conjecture describing the rational points on an elliptic curve, one of the most celebrated unsolved problems in mathematics. Here we extend the original empirical approach, to the analysis of the Cremona database of quantities relevant to BSD, inspecting more than 2.5 million elliptic curves by means of the latest techniques in data science, machine-learning and topological data analysis. Key quantities such as rank, Weierstrass coefficients, period, conductor, Tamagawa number, regulator and order of the Tate-Shafarevich group give rise to a high-dimensional point-cloud whose statistical properties we investigate. We reveal patterns and distributions in the rank versus Weierstrass coefficients, as well as the Beta distribution of the BSD ratio of the quantities. Via gradient boosted trees, machine learning is applied in finding inter-correlation amongst the various quantities. We anticipate that our approach will spark further research on the statistical properties of large datasets in Number Theory and more in general in pure Mathematics.

arXiv comment40 pages, 19 figures

References in corpus (10)

• Machine Learning of Calabi-Yau Volumes
• Machine Learning CICY Threefolds
• Deep Learning the Hyperbolic Volume of a Knot
• Getting CICY High
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Distinguishing Elliptic Fibrations with AI
• Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
• Three lectures on elliptic surfaces and curves of high rank
• A majority of elliptic curves over $\mathbb{Q}$ satisfy the Birch and Swinnerton-Dyer conjecture
• A positive proportion of elliptic curves over $\mathbb{Q}$ have rank one

Cited by in corpus (11)

• The Ramanujan Machine: Automatically Generated Conjectures on Fundamental Constants
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Machine Learning Lie Structures & Applications to Physics
• Hilbert Series, Machine Learning, and Applications to Physics
• Machine-Learning Arithmetic Curves
• Machine-Learning Number Fields
• Lectures on the Calabi-Yau Landscape
• Graph Laplacians, Riemannian Manifolds and their Machine-Learning
• Universes as Big Data
• Even Unimodular Lattices from Quaternion Algebras
• A machine learning approach to commutative algebra: Distinguishing table vs non-table ideals