Cargando…

A Quantum Graph Neural Network Approach to Particle Track Reconstruction

Unprecedented increase of complexity and scale of data is expected in computation necessary for the tracking detectors of the High Luminosity Large Hadron Collider (HL-LHC) experiments. While currently used Kalman filter based algorithms are reaching their limits in terms of ambiguities from increas...

Descripción completa

Detalles Bibliográficos
Autores principales: Tüysüz, Cenk, Carminati, Federico, Demirköz, Bilge, Dobos, Daniel, Fracas, Fabio, Novotny, Kristiane, Potamianos, Karolos, Vallecorsa, Sofia, Vlimant, Jean-Roch
Lenguaje:eng
Publicado: 2020
Materias:
Acceso en línea:https://dx.doi.org/10.5281/zenodo.4088474
http://cds.cern.ch/record/2725679
_version_ 1780966049551745024
author Tüysüz, Cenk
Carminati, Federico
Demirköz, Bilge
Dobos, Daniel
Fracas, Fabio
Novotny, Kristiane
Potamianos, Karolos
Vallecorsa, Sofia
Vlimant, Jean-Roch
author_facet Tüysüz, Cenk
Carminati, Federico
Demirköz, Bilge
Dobos, Daniel
Fracas, Fabio
Novotny, Kristiane
Potamianos, Karolos
Vallecorsa, Sofia
Vlimant, Jean-Roch
author_sort Tüysüz, Cenk
collection CERN
description Unprecedented increase of complexity and scale of data is expected in computation necessary for the tracking detectors of the High Luminosity Large Hadron Collider (HL-LHC) experiments. While currently used Kalman filter based algorithms are reaching their limits in terms of ambiguities from increasing number of simultaneous collisions, occupancy, and scalability (worse than quadratic), a variety of machine learning approaches to particle track reconstruction are explored. It has been demonstrated previously by HEP.TrkX using TrackML datasets, that graph neural networks, by processing events as a graph connecting track measurements can provide a promising solution by reducing the combinatorial background to a manageable amount and are scaling to a computationally reasonable size. In previous work, we have shown a first attempt of Quantum Computing to Graph Neural Networks for track reconstruction of particles. We aim to leverage the capability of quantum computing to evaluate a very large number of states simultaneously and thus to effectively search a large parameter space. As the next step in this paper, we present an improved model with an iterative approach to overcome the low accuracy convergence of the initial oversimplified Tree Tensor Network (TTN) model.
id cern-2725679
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2020
record_format invenio
spelling cern-27256792022-11-17T15:23:04Zdoi:10.5281/zenodo.4088474http://cds.cern.ch/record/2725679engTüysüz, CenkCarminati, FedericoDemirköz, BilgeDobos, DanielFracas, FabioNovotny, KristianePotamianos, KarolosVallecorsa, SofiaVlimant, Jean-RochA Quantum Graph Neural Network Approach to Particle Track Reconstructionquant-phGeneral Theoretical PhysicsUnprecedented increase of complexity and scale of data is expected in computation necessary for the tracking detectors of the High Luminosity Large Hadron Collider (HL-LHC) experiments. While currently used Kalman filter based algorithms are reaching their limits in terms of ambiguities from increasing number of simultaneous collisions, occupancy, and scalability (worse than quadratic), a variety of machine learning approaches to particle track reconstruction are explored. It has been demonstrated previously by HEP.TrkX using TrackML datasets, that graph neural networks, by processing events as a graph connecting track measurements can provide a promising solution by reducing the combinatorial background to a manageable amount and are scaling to a computationally reasonable size. In previous work, we have shown a first attempt of Quantum Computing to Graph Neural Networks for track reconstruction of particles. We aim to leverage the capability of quantum computing to evaluate a very large number of states simultaneously and thus to effectively search a large parameter space. As the next step in this paper, we present an improved model with an iterative approach to overcome the low accuracy convergence of the initial oversimplified Tree Tensor Network (TTN) model.arXiv:2007.06868oai:cds.cern.ch:27256792020-07-14
spellingShingle quant-ph
General Theoretical Physics
Tüysüz, Cenk
Carminati, Federico
Demirköz, Bilge
Dobos, Daniel
Fracas, Fabio
Novotny, Kristiane
Potamianos, Karolos
Vallecorsa, Sofia
Vlimant, Jean-Roch
A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title_full A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title_fullStr A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title_full_unstemmed A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title_short A Quantum Graph Neural Network Approach to Particle Track Reconstruction
title_sort quantum graph neural network approach to particle track reconstruction
topic quant-ph
General Theoretical Physics
url https://dx.doi.org/10.5281/zenodo.4088474
http://cds.cern.ch/record/2725679
work_keys_str_mv AT tuysuzcenk aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT carminatifederico aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT demirkozbilge aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT dobosdaniel aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT fracasfabio aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT novotnykristiane aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT potamianoskarolos aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT vallecorsasofia aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT vlimantjeanroch aquantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT tuysuzcenk quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT carminatifederico quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT demirkozbilge quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT dobosdaniel quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT fracasfabio quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT novotnykristiane quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT potamianoskarolos quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT vallecorsasofia quantumgraphneuralnetworkapproachtoparticletrackreconstruction
AT vlimantjeanroch quantumgraphneuralnetworkapproachtoparticletrackreconstruction