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

Keywords:

References

1. R. Altman, J. Carifio, J. Halverson and B. D. Nelson , Estimating Calabi-Yau hypersurface and triangulation counts with equation learners, J. High Energy Phys. 03 (2019) 186, arXiv:1811.06490 [hep-th]. Crossref, Google Scholar
2. R. Altman, J. Gray, Y.-H. He, V. Jejjala and B. D. Nelson , A Calabi-Yau database: Threefolds constructed from the Kreuzer-Skarke list, J. High Energy Phys. 02 (2015) 158, arXiv:1411.1418 [hep-th]. Crossref, Google Scholar
3. G. Balletti, A. M. Kasprzyk and B. Nill, On the maximum dual volume of a canonical fano polytope, preprint (2016), arXiv:1611.02455 [math.CO]. Google Scholar
4. J. Bao, S. Franco, Y.-H. He, E. Hirst, G. Musiker and Y. Xiao , Quiver mutations, Seiberg duality and machine learning, Phys. Rev. D 102(8) (2020) 086013, arXiv:2006.10783 [hep-th]. Crossref, Google Scholar
5. J. Bao, Y.-H. He and E. Hirst , Neurons on Amoebae, J. Symb. Comput. 116 (2022) 1–38, arXiv:2106.03695 [math.AG]. Crossref, Google Scholar
6. J. Bao, Y.-H. He, E. Hirst, J. Hofscheier, A. Kasprzyk and S. Majumder , Hilbert series, machine learning, and applications to physics, Phys. Lett. B 827 (2022) 136966, arXiv:2103.13436 [hep-th]. Crossref, Google Scholar
7. J. Bao, Y.-H. He, E. Hirst and S. Pietromonaco, Lectures on the Calabi-Yau landscape, preprint (2020), arXiv:2001.01212 [hep-th]. Google Scholar
8. V. V. Batyrev and L. A. Borisov , On Calabi-Yau Complete Intersections in Toric Varieties, Higher Dimensional Complex Varieties: Proc. Int. Conf. (De Gruyter, 1996), pp. 39–66, http://dx.doi.org/doi:10.1515/9783110814736.39. Google Scholar
9. V. Batyrev and J. Hofscheier, Lattice polytopes, finite abelian subgroups in $S L (n, C)$ and coding theory, preprint (2013), arXiv:1309.5312 [math.CO]. Google Scholar
10. V. Batyrev and J. Hofscheier , A generalization of a theorem of white, Mosc. J. Comb. Number Theory 10(4) (2022) 281–296. Crossref, Google Scholar
11. V. Batyrev, A. Kasprzyk and K. Schaller, On the fine interior of three-dimensional canonical Fano polytopes, preprint (2019), arXiv:1911.12048 [math.AG]. Google Scholar
12. B. Bengfort and R. Bilbro , Yellowbrick: Visualizing the Scikit-Learn model selection process, J. Open Source Softw. 4(35) (2019) 1075, http://joss.theoj.org/papers/10.21105/joss.01075. Crossref, Google Scholar
13. U. Betke and P. McMullen , Lattice points in lattice polytopes, Monatsh. Math. 99 (1985) 253–265. Crossref, Google Scholar
14. I. Borg and P. J. Groenen , Modern Multidimensional Scaling: Theory and Applications (Springer Science & Business Media, 2005). Google Scholar
15. A. Borisov, Convex lattice polytopes and cones with few lattice points inside, from a birational geometry viewpoint, preprint (2000), arXiv:math/0001109. Google Scholar
16. A. A. Borisov and L. A. Borisov , Singular toric fano varieties, Mat. Sb. 183(2) (1992) 134–141. Google Scholar
17. A. P. Braun, J. Knapp, E. Scheidegger, H. Skarke and N.-O. Walliser, PALP — A user manual, preprint (2012), arXiv:1205.4147 [math.AG]. Google Scholar
18. J. Carifio, J. Halverson, D. Krioukov and B. D. Nelson , Machine learning in the string landscape, J. High Energy Phys. 09 (2017) 157, arXiv:1707.00655 [hep-th]. Crossref, Google Scholar
19. D. Cox, J. Little and H. Schenck , Toric Varieties, Graduate Studies in Mathematics (American Mathematical Society, 2011). Crossref, Google Scholar
20. M. Demirtas, C. Long, L. McAllister and M. Stillman , The Kreuzer-Skarke axiverse, J. High Energy Phys. 04 (2020) 138, arXiv:1808.01282 [hep-th]. Crossref, Google Scholar
21. M. Demirtas, L. McAllister and A. Rios-Tascon, Bounding the Kreuzer-Skarke landscape, preprint (2020), arXiv:2008.01730 [hep-th]. Google Scholar
22. E. Ehrhart , Sur un probleme de géométrie diophantienne linéaire II, J. Reine Angew. Math. 227(25) (1967) C49. Google Scholar
23. L.-A. Gottlieb, E. Kaufman, A. Kontorovich and G. Nivasch , Learning convex polytopes with margin, in 32nd Conf. Neural Information Processing Systems (NeurIPS, 2018), pp. 5711–5721. Google Scholar
24. N. Goyal, The polytope learning problem, talk @ simons workshop on computational challenges in machine learning (2017), https://simons.berkeley.edu/ workshops/machinelearning2017-3. Google Scholar
25. Y.-H. He , Deep-learning the landscape, Phys. Lett. B 774 (2017) 564–568, arXiv:1706.02714 [hep-th]. Crossref, Google Scholar
26. Y.-H. He , The Calabi-Yau Landscape: From Geometry, to Physics, to Machine-Learning (Springer Nature, 2021). Crossref, Google Scholar
27. Y.-H. He, Machine-learning mathematical structures, preprint (2021), arXiv:2101.06317 [cs.LG]. Google Scholar
28. Y.-H. He, E. Hirst and T. Peterken , Machine-learning dessins d’enfants: explorations via modular and Seiberg–Witten curves, J. Phys. A 54(7) (2021) 075401, arXiv:2004.05218 [hep-th]. Crossref, Google Scholar
29. Y.-H. He, V. Jejjala and L. Pontiggia , Patterns in Calabi–Yau distributions, Commun. Math. Phys. 354(2) (2017) 477–524, arXiv:1512.01579 [hep-th]. Crossref, Google Scholar
30. T. Hibi and A. Tsuchiya , Algebraic and Geometric Combinatorics on Lattice Polytopes — Proc. Summer Workshop on Lattice Polytopes (World Scientific, 2019). Link, Google Scholar
31. Y.-H. He, R.-K. Seong and S.-T. Yau , Calabi–Yau volumes and reflexive polytopes, Commun. Math. Phys. 361(1) (2018) 155–204, arXiv:1704.03462 [hep-th]. Crossref, Google Scholar
32. A. M. Kasprzyk , Canonical toric fano threefolds, Can. J. Math. 62(6) (2010) 1293–1309. Crossref, Google Scholar
33. A. M. Kasprzyk and B. Nill , Reflexive polytopes of higher index and the number 12, Electron. J. Combin. 19(3) (2012) 9. Crossref, Google Scholar
34. A. M. Kasprzyk and B. Nill , Fano polytopes, in Strings, Gauge Fields, and the Geometry Behind (World Scientific Publishing, Hackensack, NJ, 2013), pp. 349–364. Google Scholar
35. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, preprint (2014), arXiv:1412.6980 [cs.LG]. Google Scholar
36. D. Krefl and R.-K. Seong , Machine learning of Calabi-Yau volumes, Phys. Rev. D 96(6) (2017) 066014, arXiv:1706.03346 [hep-th]. Crossref, Google Scholar
37. M. Kreuzer and H. Skarke , On the classification of reflexive polyhedra, Commun. Math. Phys. 185 (1997) 495–508, arXiv:hep-th/9512204. Crossref, Google Scholar
38. M. Kreuzer and H. Skarke , Classification of reflexive polyhedra in three-dimensions, Adv. Theor. Math. Phys. 2 (1998) 853–871, arXiv:hep-th/9805190. Crossref, Google Scholar
39. M. Kreuzer and H. Skarke , Complete classification of reflexive polyhedra in four-dimensions, Adv. Theor. Math. Phys. 4 (2002) 1209–1230, arXiv:hep-th/0002240. Crossref, Google Scholar
40. H. Minkowski , Geometrie der Zahlen, Geometrie der Zahlen (B. G. Teubner, 1910). Google Scholar
41. F. Pedregosa et al., Scikit-learn: Machine learning in python, J. Mach. Learn. Res. 12 (2011) 2825–2830. Google Scholar
42. B. Poonen and F. Rodriguez-Villegas , Lattice polygons and the number 12, Am. Math. Mon. 107(3) (2000) 238–250. Crossref, Google Scholar
43. A. Rebhan, L. Katzarkov and J. Knapp , Strings, Gauge Fields, and the Geometry Behind: The Legacy of Maximilian Kreuzer (World Scientific, 2013). Google Scholar
44. F. Ruehle , Evolving neural networks with genetic algorithms to study the string landscape, J. High Energy Phys. 08 (2017) 038, arXiv:1706.07024 [hep-th]. Crossref, Google Scholar
45. D. Sommerville , Introduction to the Geometry of N Dimensions, Dover Books on Mathematics (Dover Publications, 2020). Google Scholar