Machine-learning the Sato-Tate conjecture

DOI10.1016/J.JSC.2021.11.002zbMATH Open1483.11133arXiv2010.01213OpenAlexW3215218315WikidataQ113869818 ScholiaQ113869818MaRDI QIDQ2066955FDOQ2066955

Kyu-Hwan Lee, T. Oliver, Yang-Hui He

Publication date: 17 January 2022

Published in: Journal of Symbolic Computation (Search for Journal in Brave)

Abstract: We apply some of the latest techniques from machine-learning to the arithmetic of hyperelliptic curves. More precisely we show that, with impressive accuracy and confidence (between 99 and 100 percent precision), and in very short time (matter of seconds on an ordinary laptop), a Bayesian classifier can distinguish between Sato-Tate groups given a small number of Euler factors for the L-function. Our observations are in keeping with the Sato-Tate conjecture for curves of low genus. For elliptic curves, this amounts to distinguishing generic curves (with Sato-Tate group SU(2)) from those with complex multiplication. In genus 2, a principal component analysis is observed to separate the generic Sato-Tate group USp(4) from the non-generic groups. Furthermore in this case, for which there are many more non-generic possibilities than in the case of elliptic curves, we demonstrate an accurate characterisation of several Sato-Tate groups with the same identity component. Throughout, our observations are verified using known results from the literature and the data available in the LMFDB. The results in this paper suggest that a machine can be trained to learn the Sato-Tate distributions and may be able to classify curves much more efficiently than the methods available in the literature.

Full work available at URL: https://arxiv.org/abs/2010.01213

zbMATH Keywords

\(L\)-functionsclassifiersSato-Tate conjecturehyper-elliptic curvesmachine-learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) [https://portal.mardi4nfdi.de/w/index.php?search=%2211G30%22&title=Special%3ASearch&profile=advanced&fulltext=1&ns120=1 Curves of arbitrary genus or genus ( e 1) over global fields (11G30)] (L)-functions of varieties over global fields; Birch-Swinnerton-Dyer conjecture (11G40) Zeta functions and related questions in algebraic geometry (e.g., Birch-Swinnerton-Dyer conjecture) (14G10) Computational number theory (11Y99)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The elements of statistical learning. Data mining, inference, and prediction
• Rigorous computation of the endomorphism ring of a Jacobian
• Automorphy for some \(l\)-adic lifts of automorphic mod \(l\) Galois representations. II
• Quelques applications du théorème de densité de Chebotarev
• A family of Calabi-Yau varieties and potential automorphy
• Sato–Tate distributions and Galois endomorphism modules in genus 2
• The existence of infinitely many supersingular primes for every elliptic curve over \(\mathbb Q\).
• On the Sato-Tate conjecture for non-generic abelian surfaces
• Evolving neural networks with genetic algorithms to study the string landscape
• Machine learning in the string landscape
• Sato-Tate distributions of twists of \(y^2=x^5-x\) and \(y^2=x^6+1\)
• A database of genus-2 curves over the rational numbers
• Sato-Tate distributions on Abelian surfaces
• Hyperelliptic curves, L-polynomials, and random matrices
• Deep learning the hyperbolic volume of a knot
• Neural network prediction of Riemann zeta zeros

Cited In (6)

• Machine learning Lie structures \& applications to physics
• Machine Learning and Invariant Theory
• Ranks of elliptic curves and deep neural networks
• Machine Learning for Automated Theorem Proving: Learning to Solve SAT and QSAT
• Machine learning for number theory: unsupervised learning with \(L\)-functions
• Machine learning invariants of arithmetic curves

Uses Software

• Mathematica
• SageMath
• ElemStatLearn
• endomorphisms

Recommendations

• Machine Learning for Automated Theorem Proving: Learning to Solve SAT and QSAT 👍 👎
• Mathematical Theories of Machine Learning - Theory and Applications 👍 👎
• Machine Learning and Computational Mathematics 👍 👎
• From algebraic geometry to machine learning 👍 👎
• Solving the Conjugacy Decision Problem via Machine Learning 👍 👎
• Machine-learning number fields 👍 👎
• Machine learning invariants of arithmetic curves 👍 👎
• Machine learning and the Continuum Hypothesis 👍 👎
• Machine Learning and Invariant Theory 👍 👎
• Machine Learning in Pure Mathematics and Theoretical Physics 👍 👎

This page was built for publication: Machine-learning the Sato-Tate conjecture

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2066955)