Machine-learning the Sato-Tate conjecture

He, Y.-H., Lee, K.-H. and Oliver, T. 2022. Machine-learning the Sato-Tate conjecture. Journal of Symbolic Computation. 111, pp. 61-72. https://doi.org/10.1016/j.jsc.2021.11.002

TitleMachine-learning the Sato-Tate conjecture
TypeJournal article
AuthorsHe, Y.-H., Lee, K.-H. and Oliver, T.
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 efficiently.

JournalJournal of Symbolic Computation
Journal citation111, pp. 61-72
ISSN1095-855X
0747-7171
Year2022
PublisherElsevier
Accepted author manuscript
License
CC BY-NC-ND 4.0
File Access Level
Open (open metadata and files)
Digital Object Identifier (DOI)https://doi.org/10.1016/j.jsc.2021.11.002
Web address (URL)https://www.sciencedirect.com/science/article/abs/pii/S0747717121000729
Publication dates
PublishedJul 2022
Published online29 Nov 2021

Related outputs

Machine learning for number theory: unsupervised learning with L-functions
Oliver, T. 2024. Machine learning for number theory: unsupervised learning with L-functions. 8th International Congress on Mathematical Software (ICMS2024). Durham University 22 - 25 Jul 2024 Springer.

PCA, arithmetic, and murmurations
Oliver, T. 2024. PCA, arithmetic, and murmurations. Murmurations in Arithmetic. ICERM (Brown University) 06 - 08 Jul 2023 World Scientific Publishing.

Preprint: Murmurations of Dirichlet Characters
Lee, K.-H., Oliver, T. and Pozdnyakov, A. 2023. Preprint: Murmurations of Dirichlet Characters. arXiv. https://doi.org/10.48550/arXiv.2307.00256

Machine Learning Class Numbers of Real Quadratic Fields
Oliver, T., Amir, M., He, Y.-H., Lee, K.-H. and Sultanow, E. 2023. Machine Learning Class Numbers of Real Quadratic Fields. International Journal of Data Science in the Mathematical Sciences. 1 (2), pp. 107-134. https://doi.org/10.1142/s2810939223500016

Counting points on elliptic curves
Oliver, T. and Wuthrich, C. 2023. Counting points on elliptic curves. LMS newsletter. 509, pp. 31-35. https://doi.org/10.1112/NLMS

Supervised learning of arithmetic invariants
Oliver, T. 2023. Supervised learning of arithmetic invariants. in: Yang-Hui He (ed.) Machine Learning in Pure Mathematics and Theoretical Physics World Scientific Publishing. pp. 331-363

Machine learning invariants of arithmetic curves
He, Y.-H., Lee, K.-H. and Oliver, T. 2023. Machine learning invariants of arithmetic curves. Journal of Symbolic Computation. 115, pp. 478-491. https://doi.org/10.1016/j.jsc.2022.08.017

Preprint: Murmurations of Elliptic Curves
He, Y.-H., Lee, K.-H., Oliver, T. and Pozdnyakov, A. 2022. Preprint: Murmurations of Elliptic Curves. arXiv. https://doi.org/10.48550/arxiv.2204.10140

Preprint: Machine Learning Class Numbers of Real Quadratic Fields
Amir, M., He, Y.-H., Lee, K.-H., Oliver, T. and Sultanow, E. 2022. Preprint: Machine Learning Class Numbers of Real Quadratic Fields. arXiv. https://doi.org/10.48550/arxiv.2209.09283

Preprint: Convergance of Kac-Moody Eisenstein Series over a Function Field
Lee, K.-H., Liu, D. and Oliver, T. 2022. Preprint: Convergance of Kac-Moody Eisenstein Series over a Function Field. arXiv. https://doi.org/10.48550/arxiv.2203.08628

Ratios of Artin L-functions
Hochfilzer, L. and Oliver, T. 2022. Ratios of Artin L-functions. Journal of Number Theory. 236, pp. 1-40. https://doi.org/10.1016/j.jnt.2021.07.007

Machine-learning number fields
He, Y.-H., Lee, K.-H. and Oliver, T. 2022. Machine-learning number fields. Mathematics, Computation and Geometry of Data. 2 (1), pp. 49-66. https://doi.org/10.4310/MCGD.2022.v2.n1.a2

Character expansion of Kac–Moody correction factors
Lee, K.-H., Liu, D and Oliver, T. 2021. Character expansion of Kac–Moody correction factors. Pacific Journal of Mathematics. 313 (1), pp. 159-183. https://doi.org/10.2140/pjm.2021.313.159

Preprint: Twisting moduli for gl(2)
Bedert, B., Cooper, G., Oliver, T. and Zhang, P. 2020. Preprint: Twisting moduli for gl(2). arXiv. https://doi.org/10.48550/arxiv.2003.02557

Preprint: Machine-Learning the Sato-Tate Conjecture
He, Y.-H., Lee, K.-H. and Oliver, T. 2020. Preprint: Machine-Learning the Sato-Tate Conjecture. arXiv. https://doi.org/10.48550/arxiv.2010.01213

Preprint: Machine-learning number fields
He, Y.-H., Lee, K.-H. and Oliver, T. 2020. Preprint: Machine-learning number fields. arXiv. https://doi.org/10.48550/arxiv.2011.08958

Preprint: Machine-learning arithmetic curves
He, Y.-H., Lee, K.-H. and Oliver, T. 2020. Preprint: Machine-learning arithmetic curves. arXiv. https://doi.org/10.48550/arxiv.2012.04084

Twisting moduli for GL(2)
Bedert, B., Cooper, G., Oliver, T. and Zhang, P. 2020. Twisting moduli for GL(2). Journal of Number Theory. 217, pp. 142-162. https://doi.org/10.1016/j.jnt.2020.04.008

Weil's converse theorem for Maass forms and cancellation of zeros
Oliver, T. and Neururer, M. 2020. Weil's converse theorem for Maass forms and cancellation of zeros. Acta Arithmetica. 196, pp. 387-422. https://doi.org/10.4064/aa190811-3-2

Preprint: Character expansion of Kac-Moody correction factors
Lee, K.-H., Liu, D. and Oliver, T. 2019. Preprint: Character expansion of Kac-Moody correction factors. arXiv. https://doi.org/10.48550/arxiv.1911.09770

Preprint: Ratios of Artin L-functions
Hochfilzer, L. and Oliver, T. 2019. Preprint: Ratios of Artin L-functions. arXiv. https://doi.org/10.48550/arxiv.1910.02821

Preprint: Weil's Converse Theorem for Maass Forms and Cancellation of Zeros
Neururer, M. and Oliver, T. 2018. Preprint: Weil's Converse Theorem for Maass Forms and Cancellation of Zeros. arXiv. https://doi.org/10.48550/arxiv.1809.06586

A conjectural extension of Hecke’s converse theorem
Bettin, S., Bober, J., Booker, A., Conrey, B., Lee, M., Molteni, G., Oliver, T., Platt, D. and Steiner, R. 2018. A conjectural extension of Hecke’s converse theorem. The Ramanujan Journal. 47, pp. 659-684. https://doi.org/10.1007/s11139-017-9953-y

A conjectural extension of hecke's converse theorem
Bettin, S., Bober, J.W., Booker, A.R., Conrey, B., Lee, M., Molteni, G., Oliver, T., Platt, D.J. and Steiner, R.S. 2017. A conjectural extension of hecke's converse theorem. arXiv. https://doi.org/10.48550/arxiv.1704.02570

Notes on low degree L-data
Oliver, T. 2017. Notes on low degree L-data. Analytic Number Theory and Related Areas. Research Institute for Mathematical Sciences, Kyoto University 04 - 06 Nov 2015

Automorphicity and mean-periodicity
Oliver, T. 2017. Automorphicity and mean-periodicity. Journal of the Mathematical Society of Japan. 69 (1), pp. 25-51. https://doi.org/10.2969/jmsj/06910025

Zeta integrals on arithmetic surfaces
Oliver, T. 2016. Zeta integrals on arithmetic surfaces. St Petersburg Math. J.. 27, pp. 1003-1028. https://doi.org/10.1090/spmj/1432

Higher Dimensional Adeles, Mean-Periodicity and Zeta Functions of Arithmetic Surfaces
Oliver, T. 2014. Higher Dimensional Adeles, Mean-Periodicity and Zeta Functions of Arithmetic Surfaces. PhD thesis University of Nottingham School of Mathematical Sciences

Permalink - https://westminsterresearch.westminster.ac.uk/item/w4q3y/machine-learning-the-sato-tate-conjecture


Share this

Usage statistics

42 total views
20 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.