Invertible networks or partons to detector and back again

Bellagente, Marco; Butter, Anja; Kasieczka, Gregor; Plehn, Tilman; Rousselot, Armand; Winterhalder, Ramon; Ardizzone, Lynton; Köthe, Ullrich

doi:10.21468/SciPostPhys.9.5.074

SciPost Physics

Invertible networks or partons to detector and back again

Marco Bellagente, Anja Butter, Gregor Kasieczka, Tilman Plehn, Armand Rousselot, Ramon Winterhalder, Lynton Ardizzone, Ullrich Köthe

SciPost Phys. 9, 074 (2020) · published 18 November 2020

doi: 10.21468/SciPostPhys.9.5.074
pdf
Submissions/Reports

Abstract

For simulations where the forward and the inverse directions have a physics meaning, invertible neural networks are especially useful. A conditional INN can invert a detector simulation in terms of high-level observables, specifically for ZW production at the LHC. It allows for a per-event statistical interpretation. Next, we allow for a variable number of QCD jets. We unfold detector effects and QCD radiation to a pre-defined hard process, again with a per-event probabilistic interpretation over parton-level phase space.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.9.5.074
TI  - Invertible networks or partons to detector and back again
PY  - 2020/11/18
UR  - https://scipost.org/SciPostPhys.9.5.074
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 9
IS  - 5
SP  - 074
A1  - Bellagente, Marco
AU  - Butter, Anja
AU  - Kasieczka, Gregor
AU  - Plehn, Tilman
AU  - Rousselot, Armand
AU  - Winterhalder, Ramon
AU  - Ardizzone, Lynton
AU  - Köthe, Ullrich
AB  - For simulations where the forward and the inverse directions have a physics meaning, invertible neural networks are especially useful. A conditional INN can invert a detector simulation in terms of high-level observables, specifically for ZW production at the LHC. It allows for a per-event statistical interpretation. Next, we allow for a variable number of QCD jets. We unfold detector effects and QCD radiation to a pre-defined hard process, again with a per-event probabilistic interpretation over parton-level phase space.
ER  -

@Article{10.21468/SciPostPhys.9.5.074,
	title={{Invertible networks or partons to detector and back again}},
	author={Marco Bellagente and Anja Butter and Gregor Kasieczka and Tilman Plehn and Armand Rousselot and Ramon Winterhalder and Lynton Ardizzone and Ullrich Köthe},
	journal={SciPost Phys.},
	volume={9},
	pages={074},
	year={2020},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.9.5.074},
	url={https://scipost.org/10.21468/SciPostPhys.9.5.074},
}

Cited by 65

Heimel et al., MadNIS - Neural multi-channel importance sampling
SciPost Phys. 15, 141 (2023) [Crossref]
Butter et al., Kicking it off(-shell) with direct diffusion
SciPost Phys. Core 7, 064 (2024) [Crossref]
Bellagente et al., Understanding Event-Generation Networks via Uncertainties
SciPost Phys. 13, 003 (2022) [Crossref]
Morandini et al., Reconstructing axion-like particles from beam dumps with simulation-based inference
Eur. Phys. J. C 84, 200 (2024) [Crossref]
Vaselli et al., End-to-end simulation of particle physics events with flow matching and generator oversampling
Mach. Learn.: Sci. Technol. 5, 035007 (2024) [Crossref]
Nachman et al., Elsa: enhanced latent spaces for improved collider simulations
Eur. Phys. J. C 83, 843 (2023) [Crossref]
Krause et al., Anomaly detection with flow-based fast calorimeter simulators
Phys. Rev. D 110, 035036 (2024) [Crossref]
Butter et al., Two invertible networks for the matrix element method
SciPost Phys. 15, 094 (2023) [Crossref]
Faucett et al., Mapping machine-learned physics into a human-readable space
Phys. Rev. D 103, 036020 (2021) [Crossref]
Buss et al., What's anomalous in LHC jets?
SciPost Phys. 15, 168 (2023) [Crossref]
Barman et al., Top-philic machine learning
Eur. Phys. J. Spec. Top., (2024) [Crossref]
Backes et al., Event-by-event comparison between machine-learning- and transfer-matrix-based unfolding methods
Eur. Phys. J. C 84, 770 (2024) [Crossref]
Stienen et al., Phase space sampling and inference from weighted events with autoregressive flows
SciPost Phys. 10, 038 (2021) [Crossref]
Chen et al., Non-Gaussianities in collider energy flux
J. High Energ. Phys. 2022, 146 (2022) [Crossref]
Winterhalder et al., Targeting multi-loop integrals with neural networks
SciPost Phys. 12, 129 (2022) [Crossref]
Leigh et al., Faster diffusion model with improved quality for particle cloud generation
Phys. Rev. D 109, 012010 (2024) [Crossref]
Pang et al., Calorimeter shower superresolution
Phys. Rev. D 109, 092009 (2024) [Crossref]
Reichelt et al., Phenomenology of jet angularities at the LHC
J. High Energ. Phys. 2022, 131 (2022) [Crossref]
Coccaro et al., Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests
Symmetry 16, 942 (2024) [Crossref]
Leigh et al., PC-JeDi: Diffusion for particle cloud generation in high energy physics
SciPost Phys. 16, 018 (2024) [Crossref]
Noever‐Castelos et al., Model updating of wind turbine blade cross sections with invertible neural networks
Wind Energy 25, 573 (2022) [Crossref]
Butter et al., Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows
SciPost Phys. 13, 087 (2022) [Crossref]
Leigh et al., $\nu$-flows: Conditional neutrino regression
SciPost Phys. 14, 159 (2023) [Crossref]
Bieringer et al., Measuring QCD Splittings with Invertible Networks
SciPost Phys. 10, 126 (2021) [Crossref]
Krause et al., CaloFlow for CaloChallenge dataset 1
SciPost Phys. 16, 126 (2024) [Crossref]
Ilten et al., Modeling hadronization using machine learning
SciPost Phys. 14, 027 (2023) [Crossref]
Kang et al., Emission-line diagnostics of H ii regions using conditional invertible neural networks
512, 617 (2022) [Crossref]
Butter et al., Generative networks for precision enthusiasts
SciPost Phys. 14, 078 (2023) [Crossref]
Raine et al., Fast and improved neutrino reconstruction in multineutrino final states with conditional normalizing flows
Phys. Rev. D 109, 012005 (2024) [Crossref]
Arratia et al., Publishing unbinned differential cross section results
J. Inst. 17, P01024 (2022) [Crossref]
Andreev et al., Measurement of Lepton-Jet Correlation in Deep-Inelastic Scattering with the H1 Detector Using Machine Learning for Unfolding
Phys. Rev. Lett. 128, 132002 (2022) [Crossref]
Diefenbacher et al., Improving generative model-based unfolding with Schrödinger bridges
Phys. Rev. D 109, 076011 (2024) [Crossref]
Krause et al., Fast and accurate simulations of calorimeter showers with normalizing flows
Phys. Rev. D 107, 113003 (2023) [Crossref]
Matchev et al., Uncertainties associated with GAN-generated datasets in high energy physics
SciPost Phys. 12, 104 (2022) [Crossref]
Bouscasse et al., Invertible Neural Networks in Astrophysics
EPJ Web of Conferences 265, 00009 (2022) [Crossref]
Bogomolov et al., Review of unfolding methods
Phys. Usp. 66, 628 (2023) [Crossref]
Chan et al., Fitting a deep generative hadronization model
J. High Energ. Phys. 2023, 84 (2023) [Crossref]
Backes et al., An unfolding method based on conditional invertible neural networks (cINN) using iterative training
SciPost Phys. Core 7, 007 (2024) [Crossref]
Butter, Normalizing Flows for LHC Theory
J. Phys.: Conf. Ser. 2438, 012004 (2023) [Crossref]
Chan et al., Unbinned profiled unfolding
Phys. Rev. D 108, 016002 (2023) [Crossref]
Ghosh et al., Towards a deep learning model for hadronization
Phys. Rev. D 106, 096020 (2022) [Crossref]
Nölke et al., Photoacoustic Quantification of Tissue Oxygenation Using Conditional Invertible Neural Networks
IEEE Trans. Med. Imaging 43, 3366 (2024) [Crossref]
Long et al., Designing observables for measurements with deep learning
Eur. Phys. J. C 84, 776 (2024) [Crossref]
Butter et al., GANplifying event samples
SciPost Phys. 10, 139 (2021) [Crossref]
Butter et al., Machine learning and LHC event generation
SciPost Phys. 14, 079 (2023) [Crossref]
Xu et al., Generative machine learning for detector response modeling with a conditional normalizing flow
J. Inst. 19, P02003 (2024) [Crossref]
Das et al., How to understand limitations of generative networks
SciPost Phys. 16, 031 (2024) [Crossref]
Bogomolov et al., Review of unfolding methods
Успехи физических наук 193, 669 (2023) [Crossref]
Kong et al., New machine learning techniques for simulation-based inference: InferoStatic nets, kernel score estimation, and kernel likelihood ratio estimation
SciPost Phys. Codebases, 14 (2023) [Crossref]
De Vita et al., A method for inferring signal strength modifiers by conditional invertible neural networks
EPJ Web of Conf. 295, 09001 (2024) [Crossref]
Backes et al., How to GAN Event Unweighting
SciPost Phys. 10, 089 (2021) [Crossref]
Komiske et al., Preserving new physics while simultaneously unfolding all observables
Phys. Rev. D 104, 076027 (2021) [Crossref]
Ackerschott et al., Returning CP-observables to the frames they belong
SciPost Phys. 17, 001 (2024) [Crossref]
Bardhan et al., Unsupervised and lightly supervised learning in particle physics
Eur. Phys. J. Spec. Top., (2024) [Crossref]
Rousselot et al., Generative invertible quantum neural networks
SciPost Phys. 16, 146 (2024) [Crossref]
Howard et al., Learning to simulate high energy particle collisions from unlabeled data
Sci Rep 12, 7567 (2022) [Crossref]
Arratia et al., Optimizing observables with machine learning for better unfolding
J. Inst. 17, P07009 (2022) [Crossref]
Heimel et al., The MadNIS reloaded
SciPost Phys. 17, 023 (2024) [Crossref]
Chen et al., Analysis-Specific Fast Simulation at the LHC with Deep Learning
Comput Softw Big Sci 5, 15 (2021) [Crossref]
Dolan et al., Disentangling quark and gluon jets with normalizing flows
Phys. Rev. D 107, 114003 (2023) [Crossref]
Quétant et al., TURBO: The Swiss Knife of Auto-Encoders
Entropy 25, 1471 (2023) [Crossref]
Bister et al., Inference of cosmic-ray source properties by conditional invertible neural networks
Eur. Phys. J. C 82, 171 (2022) [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]
Metodiev et al., Anomaly detection in collider physics via factorized observables
Phys. Rev. D 110, 055012 (2024) [Crossref]

Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.

¹ Marco Bellagente,
¹ Anja Butter,
² Gregor Kasieczka,
¹ Tilman Plehn,
¹ Armand Rousselot,
¹ Ramon Winterhalder,
¹ Lynton Ardizzone,
¹ Ullrich Köthe

Funders for the research work leading to this publication