Cargando…
Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning
We present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets. Taking as an example the generation of W+jet events produced in sqrt(s)= 13 TeV proton-proton collisions, we train a neural network to model detector resolution effects as a...
Autores principales: | , , , , |
---|---|
Lenguaje: | eng |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2742834 |
_version_ | 1780968522950639616 |
---|---|
author | Chen, Cheng Cerri, Olmo Nguyen, Thong Q. Vlimant, Jean-Roch Pierini, Maurizio |
author_facet | Chen, Cheng Cerri, Olmo Nguyen, Thong Q. Vlimant, Jean-Roch Pierini, Maurizio |
author_sort | Chen, Cheng |
collection | CERN |
description | We present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets. Taking as an example the generation of W+jet events produced in sqrt(s)= 13 TeV proton-proton collisions, we train a neural network to model detector resolution effects as a transfer function acting on an analysis-specific set of relevant features, computed at generation level, i.e., in absence of detector effects. Based on this model, we propose a novel fast-simulation workflow that starts from a large amount of generator-level events to deliver large analysis-specific samples. The adoption of this approach would result in about an order-of-magnitude reduction in computing and storage requirements for the collision simulation workflow. This strategy could help the high energy physics community to face the computing challenges of the future High-Luminosity LHC. |
id | cern-2742834 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2020 |
record_format | invenio |
spelling | cern-27428342023-03-14T19:06:33Zhttp://cds.cern.ch/record/2742834engChen, ChengCerri, OlmoNguyen, Thong Q.Vlimant, Jean-RochPierini, MaurizioData Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learninghep-phParticle Physics - Phenomenologyhep-exParticle Physics - Experimentcs.LGComputing and Computersphysics.comp-phOther Fields of PhysicsWe present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets. Taking as an example the generation of W+jet events produced in sqrt(s)= 13 TeV proton-proton collisions, we train a neural network to model detector resolution effects as a transfer function acting on an analysis-specific set of relevant features, computed at generation level, i.e., in absence of detector effects. Based on this model, we propose a novel fast-simulation workflow that starts from a large amount of generator-level events to deliver large analysis-specific samples. The adoption of this approach would result in about an order-of-magnitude reduction in computing and storage requirements for the collision simulation workflow. This strategy could help the high energy physics community to face the computing challenges of the future High-Luminosity LHC.arXiv:2010.01835oai:cds.cern.ch:27428342020-10-05 |
spellingShingle | hep-ph Particle Physics - Phenomenology hep-ex Particle Physics - Experiment cs.LG Computing and Computers physics.comp-ph Other Fields of Physics Chen, Cheng Cerri, Olmo Nguyen, Thong Q. Vlimant, Jean-Roch Pierini, Maurizio Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title | Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title_full | Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title_fullStr | Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title_full_unstemmed | Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title_short | Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning |
title_sort | data augmentation at the lhc through analysis-specific fast simulation with deep learning |
topic | hep-ph Particle Physics - Phenomenology hep-ex Particle Physics - Experiment cs.LG Computing and Computers physics.comp-ph Other Fields of Physics |
url | http://cds.cern.ch/record/2742834 |
work_keys_str_mv | AT chencheng dataaugmentationatthelhcthroughanalysisspecificfastsimulationwithdeeplearning AT cerriolmo dataaugmentationatthelhcthroughanalysisspecificfastsimulationwithdeeplearning AT nguyenthongq dataaugmentationatthelhcthroughanalysisspecificfastsimulationwithdeeplearning AT vlimantjeanroch dataaugmentationatthelhcthroughanalysisspecificfastsimulationwithdeeplearning AT pierinimaurizio dataaugmentationatthelhcthroughanalysisspecificfastsimulationwithdeeplearning |