Targeting multi-loop integrals with neural networks

Winterhalder, Ramon; Magerya, Vitaly; Villa, Emilio; Jones, Stephen; Kerner, Matthias; Butter, Anja; Heinrich, Gudrun; Plehn, Tilman

doi:10.21468/SciPostPhys.12.4.129

SciPost Physics

Targeting multi-loop integrals with neural networks

Ramon Winterhalder, Vitaly Magerya, Emilio Villa, Stephen P. Jones, Matthias Kerner, Anja Butter, Gudrun Heinrich, Tilman Plehn

SciPost Phys. 12, 129 (2022) · published 13 April 2022

doi: 10.21468/SciPostPhys.12.4.129
pdf
Submissions/Reports

Abstract

Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this contour using a combination of optimized, global complex shifts and a normalizing flow. They can lead to a significant gain in precision.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.12.4.129
TI  - Targeting multi-loop integrals with neural networks
PY  - 2022/04/13
UR  - https://scipost.org/SciPostPhys.12.4.129
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 12
IS  - 4
SP  - 129
A1  - Winterhalder, Ramon
AU  - Magerya, Vitaly
AU  - Villa, Emilio
AU  - Jones, Stephen
AU  - Kerner, Matthias
AU  - Butter, Anja
AU  - Heinrich, Gudrun
AU  - Plehn, Tilman
AB  - Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this contour using a combination of optimized, global complex shifts and a normalizing flow. They can lead to a significant gain in precision.
ER  -

@Article{10.21468/SciPostPhys.12.4.129,
	title={{Targeting multi-loop integrals with neural networks}},
	author={Ramon Winterhalder and Vitaly Magerya and Emilio Villa and Stephen P. Jones and Matthias Kerner and Anja Butter and Gudrun Heinrich and Tilman Plehn},
	journal={SciPost Phys.},
	volume={12},
	pages={129},
	year={2022},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.12.4.129},
	url={https://scipost.org/10.21468/SciPostPhys.12.4.129},
}

Cited by 25

Quétant et al., Generating variable length full events from partons
Phys. Rev. D 110, 076023 (2024) [Crossref]
Chahrour et al., Comparing machine learning and interpolation methods for loop-level calculations
SciPost Phys. 12, 187 (2022) [Crossref]
Campbell et al., Event generators for high-energy physics experiments
SciPost Phys. 16, 130 (2024) [Crossref]
Heimel et al., Precision-machine learning for the matrix element method
SciPost Phys. 17, 129 (2024) [Crossref]
Bishara et al., High-precision regressors for particle physics
Sci Rep 14, 5294 (2024) [Crossref]
Butter et al., Two invertible networks for the matrix element method
SciPost Phys. 15, 094 (2023) [Crossref]
Huss et al., Les Houches 2021—physics at TeV colliders: report on the standard model precision wishlist
J. Phys. G: Nucl. Part. Phys. 50, 043001 (2023) [Crossref]
Heimel et al., MadNIS - Neural multi-channel importance sampling
SciPost Phys. 15, 141 (2023) [Crossref]
Nachman et al., Elsa: enhanced latent spaces for improved collider simulations
Eur. Phys. J. C 83, 843 (2023) [Crossref]
Heimel et al., The MadNIS reloaded
SciPost Phys. 17, 023 (2024) [Crossref]
Ramírez-Uribe et al., Quantum algorithm for Feynman loop integrals
J. High Energ. Phys. 2022, 100 (2022) [Crossref]
Jinno et al., Machine learning Post-Minkowskian integrals
J. High Energ. Phys. 2023, 181 (2023) [Crossref]
Calisto et al., Learning Feynman integrals from differential equations with neural networks
J. High Energ. Phys. 2024, 124 (2024) [Crossref]
Clemente et al., Variational quantum eigensolver for causal loop Feynman diagrams and directed acyclic graphs
Phys. Rev. D 108, 096035 (2023) [Crossref]
Verheyen, Event Generation and Density Estimation with Surjective Normalizing Flows
SciPost Phys. 13, 047 (2022) [Crossref]
Butter et al., Machine learning and LHC event generation
SciPost Phys. 14, 079 (2023) [Crossref]
Dolan et al., Disentangling quark and gluon jets with normalizing flows
Phys. Rev. D 107, 114003 (2023) [Crossref]
Krause et al., CaloFlow for CaloChallenge dataset 1
SciPost Phys. 16, 126 (2024) [Crossref]
De Vita et al., Acceleration beyond lowest order event generation. An outlook on further parallelism within MadGraph5_aMC@NLO
EPJ Web of Conf. 295, 10001 (2024) [Crossref]
Ilten et al., Modeling hadronization using machine learning
SciPost Phys. 14, 027 (2023) [Crossref]
Krause et al., Anomaly detection with flow-based fast calorimeter simulators
Phys. Rev. D 110, 035036 (2024) [Crossref]
Butter et al., Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows
SciPost Phys. 13, 087 (2022) [Crossref]
Butter et al., Kicking it off(-shell) with direct diffusion
SciPost Phys. Core 7, 064 (2024) [Crossref]
Armadillo et al., Evaluation of Feynman integrals with arbitrary complex masses via series expansions
Computer Physics Communications 282, 108545 108545 (2023) [Crossref]
Pang et al., Calorimeter shower superresolution
Phys. Rev. D 109, 092009 (2024) [Crossref]

Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.

¹ ² Ramon Winterhalder,
³ Vitaly Magerya,
³ Emilio Villa,
⁴ Stephen Jones,
³ Matthias Kerner,
¹ Anja Butter,
³ Gudrun Heinrich,
¹ Tilman Plehn

Funders for the research work leading to this publication

Deutsche Forschungsgemeinschaft / German Research FoundationDeutsche Forschungsgemeinschaft [DFG]
Fonds De La Recherche Scientifique - FNRS (FNRS) (through Organization: Fonds National de la Recherche Scientifique [FNRS])