[HTML][HTML] Deep generative models for detector signature simulation: A taxonomic review

B Hashemi, C Krause - Reviews in Physics, 2024 - Elsevier
In modern collider experiments, the quest to explore fundamental interactions between
elementary particles has reached unparalleled levels of precision. Signatures from particle …

Deep Generative Models for Detector Signature Simulation: A Taxonomic Review

B Hashemi, C Krause - arXiv preprint arXiv:2312.09597, 2023 - arxiv.org
In modern collider experiments, the quest to explore fundamental interactions between
elementary particles has reached unparalleled levels of precision. Signatures from particle …

Modern machine learning for LHC physicists

T Plehn, A Butter, B Dillon, T Heimel, C Krause… - arXiv preprint arXiv …, 2022 - arxiv.org
Modern machine learning is transforming particle physics fast, bullying its way into our
numerical tool box. For young researchers it is crucial to stay on top of this development …

Precision-machine learning for the matrix element method

T Heimel, N Huetsch, R Winterhalder, T Plehn… - SciPost Physics, 2024 - scipost.org
The matrix element method is the LHC inference method of choice for limited statistics. We
present a dedicated machine learning framework, based on efficient phase-space …

How to understand limitations of generative networks

R Das, L Favaro, T Heimel, C Krause, T Plehn, D Shih - SciPost Physics, 2024 - scipost.org
Well-trained classifiers and their complete weight distributions provide us with a well-
motivated and practicable method to test generative networks in particle physics. We …

The madnis reloaded

T Heimel, N Huetsch, F Maltoni, O Mattelaer, T Plehn… - SciPost Physics, 2024 - scipost.org
In pursuit of precise and fast theory predictions for the LHC, we present an implementation of
the MadNIS method in the MadGraph event generator. A series of improvements in MadNIS …

An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative training

M Backes, A Butter, M Dunford, B Malaescu - SciPost Physics Core, 2024 - scipost.org
The unfolding of detector effects is crucial for the comparison of data to theory predictions.
While traditional methods are limited to representing the data in a low number of …

Returning CP-observables to the frames they belong

J Ackerschott, RK Barman, D Gonçalves, T Heimel… - SciPost Physics, 2024 - scipost.org
Optimal kinematic observables are often defined in specific frames and then approximated
at the reconstruction level. We show how multi-dimensional unfolding methods allow us to …

CaloClouds II: ultra-fast geometry-independent highly-granular calorimeter simulation

E Buhmann, F Gaede, G Kasieczka… - Journal of …, 2024 - iopscience.iop.org
Fast simulation of the energy depositions in high-granular detectors is needed for future
collider experiments at ever-increasing luminosities. Generative machine learning (ML) …

Two invertible networks for the matrix element method

A Butter, T Heimel, T Martini, S Peitzsch, T Plehn - SciPost Physics, 2023 - scipost.org
The matrix element method is widely considered the ultimate LHC inference tool for small
event numbers. We show how a combination of two conditional generative neural networks …