Learning non-Higgsable gauge groups in 4D F-theory
arXiv:1804.07296 · doi:10.1007/JHEP08(2018)009
Abstract
We apply machine learning techniques to solve a specific classification problem in 4D F-theory. For a divisor on a given complex threefold base, we want to read out the non-Higgsable gauge group on it using local geometric information near . The input features are the triple intersection numbers among divisors near and the output label is the non-Higgsable gauge group. We use decision tree to solve this problem and achieved 85%-98% out-of-sample accuracies for different classes of divisors, where the data sets are generated from toric threefold bases without (4,6) curves. We have explicitly generated a large number of analytic rules directly from the decision tree and proved a small number of them. As a crosscheck, we applied these decision trees on bases with (4,6) curves as well and achieved high accuracies. Additionally, we have trained a decision tree to distinguish toric (4,6) curves as well. Finally, we present an application of these analytic rules to construct local base configurations with interesting gauge groups such as SU(3).
arXiv comment50 pages, 18 figures, 20 tables
References in corpus (32)
- Evidence for F-Theory
- Compactifications of F-Theory on Calabi--Yau Threefolds -- II
- Flux Compactification
- Flux compactifications in string theory: a comprehensive review
- Compactifications of F-Theory on Calabi--Yau Threefolds -- I
- Geometric Singularities and Enhanced Gauge Symmetries
- On the Classification of 6D SCFTs and Generalized ADE Orbifolds
- Atomic Classification of 6D SCFTs
- 6d Conformal Matter
- Lectures on F-theory compactifications and model building
- Matter From Geometry
- Classifying bases for 6D F-theory models
- Matter and singularities
- Tate's algorithm and F-theory
- Toric bases for 6D F-theory models
- Machine Learning in the String Landscape
- Machine Learning of Calabi-Yau Volumes
- Evolving neural networks with genetic algorithms to study the String Landscape
- On the Hodge structure of elliptically fibered Calabi-Yau threefolds
- On Algorithmic Universality in F-theory Compactifications
- Terminal Singularities, Milnor Numbers, and Matter in F-theory
- Scanning the skeleton of the 4D F-theory landscape
- Non-Higgsable clusters for 4D F-theory models
- -bundle bases and the prevalence of non-Higgsable structure in 4D F-theory models
- A Monte Carlo exploration of threefold base geometries for 4d F-theory vacua
- The Vertical, the Horizontal and the Rest: anatomy of the middle cohomology of Calabi-Yau fourfolds and F-theory applications
- Non-Higgsable QCD and the Standard Model Spectrum in F-theory
- Codimension-Three Bundle Singularities in F-Theory
- Enhanced gauge symmetry in 6D F-theory models and tuned elliptic Calabi-Yau threefolds
- Tuned and Non-Higgsable U(1)s in F-theory
- Statistics of Flux Vacua for Particle Physics
- Distribution of the Number of Generations in Flux Compactifications
Cited by in corpus (12)
- Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
- Machine learning Calabi-Yau metrics
- Searching the Landscape of Flux Vacua with Genetic Algorithms
- Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
- Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
- Explore and Exploit with Heterotic Line Bundle Models
- Statistical Predictions in String Theory and Deep Generative Models
- Accessibility Measure for Eternal Inflation: Dynamical Criticality and Higgs Metastability
- Applying machine learning to the Calabi-Yau orientifolds with string vacua
- Learning to Inflate
- Universes as Big Data
- Machine Learning on generalized Complete Intersection Calabi-Yau Manifolds