Machine Learning and Algebraic Approaches towards Complete Matter Spectra in 4d F-theory

Abstract

Motivated by engineering vector-like (Higgs) pairs in the spectrum of 4d F-theory compactifications, we combine machine learning and algebraic geometry techniques to analyze line bundle cohomologies on families of holomorphic curves. To quantify jumps of these cohomologies, we first generate 1.8 million pairs of line bundles and curves embedded in $d{P}_3$, for which we compute the cohomologies. A white-box machine learning approach trained on this data provides intuition for jumps due to curve splittings, which we use to construct additional vector-like Higgs-pairs in an F-Theory toy model. We also find that, in order to explain quantitatively the full dataset, further tools from algebraic geometry, in particular Brill--Noether theory, are required. Using these ingredients, we introduce a diagrammatic way to express cohomology jumps across the parameter space of each family of matter curves, which reflects a stratification of the F-theory complex structure moduli space in terms of the vector-like spectrum. Furthermore, these insights provide an algorithmically efficient way to estimate the possible cohomology dimensions across the entire parameter space.

42 pages + appendix

References in corpus (11)

• Heterotic Compactification, An Algorithmic Approach
• Machine Learning in the String Landscape
• Machine Learning of Calabi-Yau Volumes
• Cohomology of Line Bundles: A Computational Algorithm
• Evolving neural networks with genetic algorithms to study the String Landscape
• Tri-linear Couplings in an Heterotic Minimal Supersymmetric Standard Model
• The Vertical, the Horizontal and the Rest: anatomy of the middle cohomology of Calabi-Yau fourfolds and F-theory applications
• Gauge Backgrounds and Zero-Mode Counting in F-Theory
• Cohomology of Line Bundles: Proof of the Algorithm
• Instantons and Hilbert Functions
• Heterotic Instantons for Monad and Extension Bundles

Cited by in corpus (13)

• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Applying machine learning to the Calabi-Yau orientifolds with string vacua
• Root Bundles and Towards Exact Matter Spectra of F-theory MSSMs
• Disentangling a Deep Learned Volume Formula
• A Triumvirate of AI Driven Theoretical Discovery
• On the Search for Low $W_0$
• Statistics of Limit Root Bundles Relevant for Exact Matter Spectra of F-Theory MSSMs
• Brill-Noether-general Limit Root Bundles: Absence of vector-like Exotics in F-theory Standard Models
• Gauge symmetry breaking with fluxes and natural Standard Model structure from exceptional GUTs in F-theory
• Machine Learning on generalized Complete Intersection Calabi-Yau Manifolds
• Generative AI for Brane Configurations and Coamoeba
• Improved statistics for F-theory standard models
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation