dc.contributor.author | Bao, J | en_US |
dc.contributor.author | He, YH | en_US |
dc.contributor.author | Hirst, E | en_US |
dc.contributor.author | Hofscheier, J | en_US |
dc.contributor.author | Kasprzyk, A | en_US |
dc.contributor.author | Majumder, S | en_US |
dc.date.accessioned | 2024-02-23T11:49:34Z | |
dc.date.issued | 2022-04-10 | en_US |
dc.identifier.issn | 0370-2693 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/94866 | |
dc.description.abstract | We describe how simple machine learning methods successfully predict geometric properties from Hilbert series (HS). Regressors predict embedding weights in projective space to ∼1 mean absolute error, whilst classifiers predict dimension and Gorenstein index to >90% accuracy with ∼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. | en_US |
dc.relation.ispartof | Physics Letters, Section B: Nuclear, Elementary Particle and High-Energy Physics | en_US |
dc.rights | This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). | |
dc.title | Hilbert series, machine learning, and applications to physics | en_US |
dc.type | Article | |
dc.rights.holder | © 2022 The Author(s). Published by Elsevier B.V. | |
dc.identifier.doi | 10.1016/j.physletb.2022.136966 | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 827 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |