CYJAX: A package for Calabi-Yau metrics with JAX

Abstract

We present the first version of CYJAX, a package for machine learning Calabi-Yau metrics using JAX. It is meant to be accessible both as a top-level tool and as a library of modular functions. CYJAX is currently centered around the algebraic ansatz for the Kähler potential which automatically satisfies Kählerity and compatibility on patch overlaps. As of now, this implementation is limited to varieties defined by a single defining equation on one complex projective space. We comment on some planned generalizations.

17 pages, 5 figures; minor corrections of code examples & clarifications; documentation at https://cyjax.readthedocs.io and code at https://github.com/ml4physics/cyjax

References in corpus (4)

• Numerical Calabi-Yau metrics
• Machine Learned Calabi-Yau Metrics and Curvature
• CYTools: A Software Package for Analyzing Calabi-Yau Manifolds
• Neural Network Approximations for Calabi-Yau Metrics

Cited by in corpus (6)

• Metric Flows with Neural Networks
• Numerical spectra of the Laplacian for line bundles on Calabi-Yau hypersurfaces
• Level Crossings, Attractor Points and Complex Multiplication
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation
• cymyc -- Calabi-Yau Metrics, Yukawas, and Curvature
• AInstein: Numerical Einstein Metrics via Machine Learning