Polytopes and Machine Learning

Abstract

We introduce machine learning methodology to the study of lattice polytopes. With supervised learning techniques, we predict standard properties such as volume, dual volume, reflexivity, etc, with accuracies up to 100%. We focus on 2d polygons and 3d polytopes with Plücker coordinates as input, which out-perform the usual vertex representation.

33 pages, 26 figures

References in corpus (6)

• Machine Learning of Calabi-Yau Volumes
• Machine Learning in the String Landscape
• A Calabi-Yau Database: Threefolds Constructed from the Kreuzer-Skarke List
• Evolving neural networks with genetic algorithms to study the String Landscape
• Hilbert Series, Machine Learning, and Applications to Physics
• Neurons on Amoebae

Cited by in corpus (4)

• Applying machine learning to the Calabi-Yau orientifolds with string vacua
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation
• Totally Positive Matrices and the Highest-Order Coefficients of the Characteristic Polynomial
• Learning 3-Manifold Triangulations