Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning

Abstract Integration-by-parts reductions of Feynman integrals pose a frequent bottleneck in state-of-the-art calculations in theoretical particle and gravitational-wave physics, and rely on heuristic approaches for selecting integration-by-parts identities, whose quality heavily influences the perfo...

Full description

Saved in:
Bibliographic Details
Main Authors: Matt von Hippel, Matthias Wilhelm
Format: Article
Language:English
Published: SpringerOpen 2025-05-01
Series:Journal of High Energy Physics
Subjects:
Online Access:https://doi.org/10.1007/JHEP05(2025)185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849470080897777664
author Matt von Hippel
Matthias Wilhelm
author_facet Matt von Hippel
Matthias Wilhelm
author_sort Matt von Hippel
collection DOAJ
description Abstract Integration-by-parts reductions of Feynman integrals pose a frequent bottleneck in state-of-the-art calculations in theoretical particle and gravitational-wave physics, and rely on heuristic approaches for selecting integration-by-parts identities, whose quality heavily influences the performance. In this paper, we investigate the use of machine-learning techniques to find improved heuristics. We use funsearch, a genetic programming variant based on code generation by a Large Language Model, in order to explore possible approaches, then use strongly typed genetic programming to zero in on useful solutions. Both approaches manage to re-discover the state-of-the-art heuristics recently incorporated into integration-by-parts solvers, and in one example find a small advance on this state of the art.
format Article
id doaj-art-795282bf820f4dd9b2daca6d3badcccd
institution Kabale University
issn 1029-8479
language English
publishDate 2025-05-01
publisher SpringerOpen
record_format Article
series Journal of High Energy Physics
spelling doaj-art-795282bf820f4dd9b2daca6d3badcccd2025-08-20T03:25:15ZengSpringerOpenJournal of High Energy Physics1029-84792025-05-012025512610.1007/JHEP05(2025)185Refining Integration-by-Parts Reduction of Feynman Integrals with Machine LearningMatt von Hippel0Matthias Wilhelm1Niels Bohr International Academy, Niels Bohr Institute, University of CopenhagenNiels Bohr International Academy, Niels Bohr Institute, University of CopenhagenAbstract Integration-by-parts reductions of Feynman integrals pose a frequent bottleneck in state-of-the-art calculations in theoretical particle and gravitational-wave physics, and rely on heuristic approaches for selecting integration-by-parts identities, whose quality heavily influences the performance. In this paper, we investigate the use of machine-learning techniques to find improved heuristics. We use funsearch, a genetic programming variant based on code generation by a Large Language Model, in order to explore possible approaches, then use strongly typed genetic programming to zero in on useful solutions. Both approaches manage to re-discover the state-of-the-art heuristics recently incorporated into integration-by-parts solvers, and in one example find a small advance on this state of the art.https://doi.org/10.1007/JHEP05(2025)185Scattering AmplitudesAutomationElectroweak Precision Physics
spellingShingle Matt von Hippel
Matthias Wilhelm
Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
Journal of High Energy Physics
Scattering Amplitudes
Automation
Electroweak Precision Physics
title Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
title_full Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
title_fullStr Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
title_full_unstemmed Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
title_short Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
title_sort refining integration by parts reduction of feynman integrals with machine learning
topic Scattering Amplitudes
Automation
Electroweak Precision Physics
url https://doi.org/10.1007/JHEP05(2025)185
work_keys_str_mv AT mattvonhippel refiningintegrationbypartsreductionoffeynmanintegralswithmachinelearning
AT matthiaswilhelm refiningintegrationbypartsreductionoffeynmanintegralswithmachinelearning