Exploring phase space with Neural Importance Sampling

Bothmann, Enrico; Janßen, Timo; Knobbe, Max; Schmale, Tobias; Schumann, Steffen

doi:10.21468/SciPostPhys.8.4.069

SciPost Physics

Exploring phase space with Neural Importance Sampling

Enrico Bothmann, Timo Janßen, Max Knobbe, Tobias Schmale, Steffen Schumann

SciPost Phys. 8, 069 (2020) · published 29 April 2020

doi: 10.21468/SciPostPhys.8.4.069
pdf
Submissions/Reports

Abstract

We present a novel approach for the integration of scattering cross sections and the generation of partonic event samples in high-energy physics. We propose an importance sampling technique capable of overcoming typical deficiencies of existing approaches by incorporating neural networks. The method guarantees full phase space coverage and the exact reproduction of the desired target distribution, in our case given by the squared transition matrix element. We study the performance of the algorithm for a few representative examples, including top-quark pair production and gluon scattering into three- and four-gluon final states.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.8.4.069
TI  - Exploring phase space with Neural Importance Sampling
PY  - 2020/04/29
UR  - https://www.scipost.org/SciPostPhys.8.4.069
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 8
IS  - 4
SP  - 069
A1  - Bothmann, Enrico
AU  - Janßen, Timo
AU  - Knobbe, Max
AU  - Schmale, Tobias
AU  - Schumann, Steffen
AB  - We present a novel approach for the integration of scattering cross sections and the generation of partonic event samples in high-energy physics. We propose an importance sampling technique capable of overcoming typical deficiencies of existing approaches by incorporating neural networks. The method guarantees full phase space coverage and the exact reproduction of the desired target distribution, in our case given by the squared transition matrix element. We study the performance of the algorithm for a few representative examples, including top-quark pair production and gluon scattering into three- and four-gluon final states.
ER  -

@Article{10.21468/SciPostPhys.8.4.069,
	title={{Exploring phase space with Neural Importance Sampling}},
	author={Enrico Bothmann and Timo Janßen and Max Knobbe and Tobias Schmale and Steffen Schumann},
	journal={SciPost Phys.},
	volume={8},
	pages={069},
	year={2020},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.8.4.069},
	url={https://scipost.org/10.21468/SciPostPhys.8.4.069},
}

Cited by 67

Afanasev et al., Radiative corrections: from medium to high energy experiments
Eur. Phys. J. A 60, 91 (2024) [Crossref]
Bury et al., Matrix element regression with deep neural networks — Breaking the CPU barrier
J. High Energ. Phys. 2021, 20 (2021) [Crossref]
Heinrich et al., Differentiable Matrix Elements with MadJax
J. Phys.: Conf. Ser. 2438, 012137 (2023) [Crossref]
Buhmann et al., Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
Comput Softw Big Sci 5, 13 (2021) [Crossref]
Yallup et al., Exploring phase space with nested sampling
Eur. Phys. J. C 82, 678 (2022) [Crossref]
Deutschmann et al., Accelerating HEP simulations with Neural Importance Sampling
J. High Energ. Phys. 2024, 83 (2024) [Crossref]
Maître et al., Multi-variable integration with a neural network
J. High Energ. Phys. 2023, 221 (2023) [Crossref]
Pina-Otey et al., Exhaustive neural importance sampling applied to Monte Carlo event generation
Phys. Rev. D 102, 013003 (2020) [Crossref]
Cruz-Martinez et al., Multi-variable integration with a variational quantum circuit
Quantum Sci. Technol. 9, 035053 (2024) [Crossref]
Bellagente et al., Understanding Event-Generation Networks via Uncertainties
SciPost Phys. 13, 003 (2022) [Crossref]
Butter et al., Kicking it off(-shell) with direct diffusion
SciPost Phys. Core 7, 064 (2024) [Crossref]
Heimel et al., MadNIS - Neural multi-channel importance sampling
SciPost Phys. 15, 141 (2023) [Crossref]
Isaacson et al., Novel event generator for the automated simulation of neutrino scattering
Phys. Rev. D 105, 096006 (2022) [Crossref]
Ilten et al., Modeling hadronization using machine learning
SciPost Phys. 14, 027 (2023) [Crossref]
Winterhalder et al., Targeting multi-loop integrals with neural networks
SciPost Phys. 12, 129 (2022) [Crossref]
Butter et al., Two invertible networks for the matrix element method
SciPost Phys. 15, 094 (2023) [Crossref]
Maître et al., A factorisation-aware Matrix element emulator
J. High Energ. Phys. 2021, 66 (2021) [Crossref]
Aylett-Bullock et al., Optimising simulations for diphoton production at hadron colliders using amplitude neural networks
J. High Energ. Phys. 2021, 66 (2021) [Crossref]
Karagiorgi et al., Machine learning in the search for new fundamental physics
Nat Rev Phys 4, 399 (2022) [Crossref]
Jinno et al., Machine learning Post-Minkowskian integrals
J. High Energ. Phys. 2023, 181 (2023) [Crossref]
Verheyen, Event Generation and Density Estimation with Surjective Normalizing Flows
SciPost Phys. 13, 047 (2022) [Crossref]
Campbell et al., Event generators for high-energy physics experiments
SciPost Phys. 16, 130 (2024) [Crossref]
Baldi et al., How to GAN Higher Jet Resolution
SciPost Phys. 13, 064 (2022) [Crossref]
Mattelaer et al., Speeding up MadGraph5_aMC@NLO
Eur. Phys. J. C 81, 435 (2021) [Crossref]
Butter et al., Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows
SciPost Phys. 13, 087 (2022) [Crossref]
et al., Challenges in Monte Carlo Event Generator Software for High-Luminosity LHC
Comput Softw Big Sci 5, 12 (2021) [Crossref]
Janßen et al., Machine learning efforts in Sherpa
J. Phys.: Conf. Ser. 2438, 012144 (2023) [Crossref]
Shyamsundar et al., Variance reduction via simultaneous importance sampling and control variates techniques using vegas
SciPost Phys. Codebases, 28 (2024) [Crossref]
Nachman et al., Neural resampler for Monte Carlo reweighting with preserved uncertainties
Phys. Rev. D 102, 076004 (2020) [Crossref]
Das et al., How to understand limitations of generative networks
SciPost Phys. 16, 031 (2024) [Crossref]
Bothmann et al., Efficient phase-space generation for hadron collider event simulation
SciPost Phys. 15, 169 (2023) [Crossref]
Dolan et al., Disentangling quark and gluon jets with normalizing flows
Phys. Rev. D 107, 114003 (2023) [Crossref]
Krause et al., Anomaly detection with flow-based fast calorimeter simulators
Phys. Rev. D 110, 035036 (2024) [Crossref]
Isaacson, Generators and the (Accelerated) Future
J. Phys.: Conf. Ser. 2438, 012001 (2023) [Crossref]
Hassanaly et al., Uniform-in-phase-space data selection with iterative normalizing flows
DCE 4, e11 (2023) [Crossref]
Butter et al., GANplifying event samples
SciPost Phys. 10, 139 (2021) [Crossref]
Maître et al., One-loop matrix element emulation with factorisation awareness
J. High Energ. Phys. 2023, 159 (2023) [Crossref]
Bellagente et al., Invertible networks or partons to detector and back again
SciPost Phys. 9, 074 (2020) [Crossref]
Andersen et al., Unbiased elimination of negative weights in Monte Carlo samples
Eur. Phys. J. C 82, 433 (2022) [Crossref]
Brady et al., Normalizing Flows for Microscopic Many-Body Calculations: An Application to the Nuclear Equation of State
Phys. Rev. Lett. 127, 062701 (2021) [Crossref]
Capatti et al., Local Unitarity: a representation of differential cross-sections that is locally free of infrared singularities at any order
J. High Energ. Phys. 2021, 104 (2021) [Crossref]
Butter et al., Machine learning and LHC event generation
SciPost Phys. 14, 079 (2023) [Crossref]
Andersen et al., Efficient negative-weight elimination in large high-multiplicity Monte Carlo event samples
Eur. Phys. J. C 83, 835 (2023) [Crossref]
Chen et al., Improved neural network Monte Carlo simulation
SciPost Phys. 10, 023 (2021) [Crossref]
Badger et al., Loop amplitudes from precision networks
SciPost Phys. Core 6, 034 (2023) [Crossref]
Backes et al., How to GAN Event Unweighting
SciPost Phys. 10, 089 (2021) [Crossref]
Heimel et al., The MadNIS reloaded
SciPost Phys. 17, 023 (2024) [Crossref]
Ghosh et al., Towards a deep learning model for hadronization
Phys. Rev. D 106, 096020 (2022) [Crossref]
Klimek et al., Neural network-based approach to phase space integration
SciPost Phys. 9, 053 (2020) [Crossref]
Matchev et al., OASIS: Optimal Analysis-Specific Importance Sampling for event generation
SciPost Phys. 10, 034 (2021) [Crossref]
Bothmann et al., A portable parton-level event generator for the high-luminosity LHC
SciPost Phys. 17, 081 (2024) [Crossref]
Buss et al., Convolutional L2LFlows: generating accurate showers in highly granular calorimeters using convolutional normalizing flows
J. Inst. 19, P09003 (2024) [Crossref]
Buarque Franzosi et al., Vector boson scattering processes: Status and prospects
Reviews in Physics 8, 100071 100071 (2022) [Crossref]
Butter et al., Generative networks for precision enthusiasts
SciPost Phys. 14, 078 (2023) [Crossref]
Bieringer et al., Measuring QCD Splittings with Invertible Networks
SciPost Phys. 10, 126 (2021) [Crossref]
Janßen et al., Unweighting multijet event generation using factorisation-aware neural networks
SciPost Phys. 15, 107 (2023) [Crossref]
Gao et al., i- flow: High-dimensional integration and sampling with normalizing flows
Mach. Learn.: Sci. Technol. 1, 045023 (2020) [Crossref]
Matchev et al., Uncertainties associated with GAN-generated datasets in high energy physics
SciPost Phys. 12, 104 (2022) [Crossref]
Danziger et al., Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates
SciPost Phys. 12, 164 (2022) [Crossref]
Pang et al., Calorimeter shower superresolution
Phys. Rev. D 109, 092009 (2024) [Crossref]
Krause et al., Fast and accurate simulations of calorimeter showers with normalizing flows
Phys. Rev. D 107, 113003 (2023) [Crossref]
Badger et al., Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
J. High Energ. Phys. 2020, 114 (2020) [Crossref]
Butter, Normalizing Flows for LHC Theory
J. Phys.: Conf. Ser. 2438, 012004 (2023) [Crossref]
Stienen et al., Phase space sampling and inference from weighted events with autoregressive flows
SciPost Phys. 10, 038 (2021) [Crossref]
Chakraborty et al., Neural network-based top tagger with two-point energy correlations and geometry of soft emissions
J. High Energ. Phys. 2020, 111 (2020) [Crossref]
Krause et al., CaloFlow for CaloChallenge dataset 1
SciPost Phys. 16, 126 (2024) [Crossref]
Park et al., Quasi anomalous knowledge: searching for new physics with embedded knowledge
J. High Energ. Phys. 2021, 30 (2021) [Crossref]

Ontology / Topics

See full Ontology or Topics database.

Gluons Neural networks Top quark

Authors / Affiliation: mappings to Contributors and Organizations

See all Organizations.

¹ Enrico Bothmann,
¹ Timo Janßen,
¹ Max Knobbe,
¹ Tobias Schmale,
¹ Steffen Schumann

¹ Georg-August-Universität Göttingen / University of Göttingen [GAU]

Funders for the research work leading to this publication

Fulbright Association
Horizon 2020 (through Organization: European Commission [EC])