Polytopes and machine learning

Bao, Jiakang; He, Yang-Hui; Hirst, Edward; Hofscheier, Johannes; Kasprzyk, Alexander; Majumder, Suvajit

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.

Citation

Bao, J., He, Y.-H., Hirst, E., Hofscheier, J., Kasprzyk, A., & Majumder, S. (2023). Polytopes and machine learning. International Journal of Data Science in the Mathematical Sciences, 1(2), 181-211. https://doi.org/10.1142/S281093922350003X

• Journal Article Type: Article
• Acceptance Date: Dec 13, 2023
• Online Publication Date: Feb 15, 2024
• Publication Date: 2023-12
• Deposit Date: Mar 29, 2024
• Publicly Available Date: Apr 3, 2024
• Print ISSN: 2810-9392
• Electronic ISSN: 2810-9406
• Publisher: World Scientific
• Peer Reviewed: Peer Reviewed
• Volume: 1
• Issue: 2
• Pages: 181-211
• Series ISSN: 2810-9392
• DOI: https://doi.org/10.1142/S281093922350003X
• Public URL: https://nottingham-repository.worktribe.com/output/23494621
• Publisher URL: https://www.worldscientific.com/doi/10.1142/S281093922350003X