Hilbert Series, Machine Learning, and Applications to Physics

Abstract

We describe how simple machine learning methods successfully predict geometric properties from Hilbert series (HS). Regressors predict embedding weights in projective space to $\sim 1$ mean absolute error, whilst classifiers predict dimension and Gorenstein index to $>90\%$ accuracy with $\sim 0.5\%$ standard error. Binary random forest classifiers managed to distinguish whether the underlying HS describes a complete intersection with high accuracies exceeding $95\%$. Neural networks (NNs) exhibited success identifying HS from a Gorenstein ring to the same order of accuracy, whilst generation of 'fake' HS proved trivial for NNs to distinguish from those associated to the three-dimensional Fano varieties considered.

arXiv comment10 pages; v2: principle component analysis added; v3: minor corrections

References in corpus (35)

• Counting Gauge Invariants: the Plethystic Program
• Monopole operators and Hilbert series of Coulomb branches of 3d N = 4 gauge theories
• Varieties of vacua in classical supersymmetric gauge theories
• Low-derivative operators of the Standard Model effective field theory via Hilbert series methods
• Hilbert Series for Constructing Lagrangians: expanding the phenomenologist's toolbox
• Hilbert series and operator bases with derivatives in effective field theories
• SQCD: A Geometric Apercu
• Heterotic Compactification, An Algorithmic Approach
• Machine Learning of Calabi-Yau Volumes
• Machine Learning CICY Threefolds
• Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
• Hilbert Series for Flavor Invariants of the Standard Model
• The Hilbert Series of Adjoint SQCD
• Machine learning Calabi-Yau metrics
• Numerical Algebraic Geometry: A New Perspective on String and Gauge Theories
• 2, 12, 117, 1959, 45171, 1170086, ...: A Hilbert series for the QCD chiral Lagrangian
• Machine Learning Line Bundle Cohomology
• Hilbert Series and Operator Basis for NRQED and NRQCD/HQET
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Quiver Mutations, Seiberg Duality and Machine Learning
• Distinguishing Elliptic Fibrations with AI
• ..., 83106786, 114382724, 1509048322, 2343463290, 27410087742, ... Efficient Hilbert Series for Effective Theories
• Explore and Exploit with Heterotic Line Bundle Models
• Hilbert Series and Plethystics: Paving the path towards 2HDM- and MLRSM-EFT
• Machine-Learning Dessins d'Enfants: Explorations via Modular and Seiberg-Witten Curves
• Statistical Predictions in String Theory and Deep Generative Models
• The Hilbert series of U/SU SQCD and Toeplitz Determinants
• Machine Learning meets Number Theory: The Data Science of Birch-Swinnerton-Dyer
• Instantons and Hilbert Functions
• Graph Laplacians, Riemannian Manifolds and their Machine-Learning
• Veronese Geometry and the Electroweak Vacuum Moduli Space
• New results for the SQCD Hilbert series
• Standard Model Plethystics
• Baryons from Mesons: A Machine Learning Perspective
• Counting Points and Hilbert Series in String Theory

Cited by in corpus (11)

• Neurons on Amoebae
• A Triumvirate of AI Driven Theoretical Discovery
• Brain Webs for Brane Webs
• Machine learning Sasakian and $G_2$ topology on contact Calabi-Yau $7$-manifolds
• Polytopes and Machine Learning
• Cluster Algebras: Network Science and Machine Learning
• Learning BPS Spectra and the Gap Conjecture
• Some Open Questions in Quiver Gauge Theory
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation
• Machine Learning Clifford invariants of ADE Coxeter elements
• Learning 3-Manifold Triangulations