Machine-learning classifiers, especially a multi-head attention model, correctly identify almost all free Z2, Z3, Z4, and Z2xZ2 quotients of CICYs on held-out manifolds, with only three missed Z2xZ2 cases.
Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We provide the first estimate of the number of fine, regular, star triangulations of the four-dimensional reflexive polytopes, as classified by Kreuzer and Skarke (KS). This provides an upper bound on the number of Calabi-Yau threefold hypersurfaces in toric varieties. The estimate is performed with deep learning, specifically the novel equation learner (EQL) architecture. We demonstrate that EQL networks accurately predict numbers of triangulations far beyond the $h^{1,1}$ training region, allowing for reliable extrapolation. We estimate that number of triangulations in the KS dataset is $10^{10,505}$, dominated by the polytope with the highest $h^{1,1}$ value.
citation-role summary
background 1
citation-polarity summary
fields
hep-th 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Machine Learning Free Quotients of CICYs
Machine-learning classifiers, especially a multi-head attention model, correctly identify almost all free Z2, Z3, Z4, and Z2xZ2 quotients of CICYs on held-out manifolds, with only three missed Z2xZ2 cases.