Machine learning Calabi-Yau metrics

@article{Ashmore2019MachineLC,
  title={Machine learning Calabi-Yau metrics},
  author={A. Ashmore and Yanghui He and B. Ovrut},
  journal={arXiv: High Energy Physics - Theory},
  year={2019}
}
  • A. Ashmore, Yanghui He, B. Ovrut
  • Published 2019
  • Mathematics, Physics
  • arXiv: High Energy Physics - Theory
  • We apply machine learning to the problem of finding numerical Calabi-Yau metrics. Building on Donaldson's algorithm for calculating balanced metrics on K\"ahler manifolds, we combine conventional curve fitting and machine-learning techniques to numerically approximate Ricci-flat metrics. We show that machine learning is able to predict the Calabi-Yau metric and quantities associated with it, such as its determinant, having seen only a small sample of training data. Using this in conjunction… CONTINUE READING
    21 Citations
    arXiv : Moduli-dependent Calabi-Yau and SU(3)-structure metrics from Machine Learning
    • 2
    • Highly Influenced
    • PDF
    Numerical Calabi-Yau metrics from holomorphic networks.
    • 4
    • PDF
    Machine-Learning Mathematical Structures
    • 1
    • PDF
    Machine-Learning Number Fields
    • 1
    • PDF
    Machine-Learning the Sato--Tate Conjecture
    • 4
    • PDF

    References

    SHOWING 1-10 OF 81 REFERENCES
    Machine learning CICY threefolds
    • 36
    • PDF
    Getting CICY High
    • 21
    • PDF
    Distinguishing Elliptic Fibrations with AI
    • 22
    • PDF
    Machine-learning the string landscape
    • 60
    • PDF
    Learning Algebraic Structures: Preliminary Investigations
    • 12
    • PDF
    Numerical Ricci-flat metrics on K3
    • 61
    • PDF
    (Machine) learning to do more with less
    • 63
    • PDF
    Machine learning of Calabi-Yau volumes
    • 55
    • PDF