Unravelling physics beyond the standard model with classical and quantum anomaly detection
Much hope for finding new physics phenomena at microscopic scale relies on the observations obtained from High Energy Physics experiments, like the ones performed at the Large Hadron Collider (LHC). However, current experiments do not indicate clear signs of new physics that could guide the developm...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad07f7 |
| _version_ | 1797626850304851968 |
|---|---|
| author | Julian Schuhmacher Laura Boggia Vasilis Belis Ema Puljak Michele Grossi Maurizio Pierini Sofia Vallecorsa Francesco Tacchino Panagiotis Barkoutsos Ivano Tavernelli |
| author_facet | Julian Schuhmacher Laura Boggia Vasilis Belis Ema Puljak Michele Grossi Maurizio Pierini Sofia Vallecorsa Francesco Tacchino Panagiotis Barkoutsos Ivano Tavernelli |
| author_sort | Julian Schuhmacher |
| collection | DOAJ |
| description | Much hope for finding new physics phenomena at microscopic scale relies on the observations obtained from High Energy Physics experiments, like the ones performed at the Large Hadron Collider (LHC). However, current experiments do not indicate clear signs of new physics that could guide the development of additional Beyond Standard Model (BSM) theories. Identifying signatures of new physics out of the enormous amount of data produced at the LHC falls into the class of anomaly detection and constitutes one of the greatest computational challenges. In this article, we propose a novel strategy to perform anomaly detection in a supervised learning setting, based on the artificial creation of anomalies through a random process. For the resulting supervised learning problem, we successfully apply classical and quantum support vector classifiers (CSVC and QSVC respectively) to identify the artificial anomalies among the SM events. Even more promising, we find that employing an SVC trained to identify the artificial anomalies, it is possible to identify realistic BSM events with high accuracy. In parallel, we also explore the potential of quantum algorithms for improving the classification accuracy and provide plausible conditions for the best exploitation of this novel computational paradigm. |
| first_indexed | 2024-03-11T10:16:04Z |
| format | Article |
| id | doaj.art-bbfc10e34e89401da69041beeb2c7420 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-11T10:16:04Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-bbfc10e34e89401da69041beeb2c74202023-11-16T08:36:39ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014404503110.1088/2632-2153/ad07f7Unravelling physics beyond the standard model with classical and quantum anomaly detectionJulian Schuhmacher0https://orcid.org/0000-0002-7011-6477Laura Boggia1https://orcid.org/0000-0002-9924-7489Vasilis Belis2https://orcid.org/0000-0001-5920-8998Ema Puljak3https://orcid.org/0000-0002-6011-9965Michele Grossi4https://orcid.org/0000-0003-1718-1314Maurizio Pierini5https://orcid.org/0000-0003-1939-4268Sofia Vallecorsa6https://orcid.org/0000-0002-7003-5765Francesco Tacchino7https://orcid.org/0000-0003-2008-5956Panagiotis Barkoutsos8https://orcid.org/0000-0001-9428-913XIvano Tavernelli9https://orcid.org/0000-0001-5690-1981IBM Quantum, IBM Research Europe - Zurich , Rüschlikon 8803, SwitzerlandIBM Quantum, IBM Research Europe - Zurich , Rüschlikon 8803, Switzerland; Institute for Theoretical Physics, ETH Zürich , 8093 Zürich, SwitzerlandInstitute for Particle Physics and Astrophysics, ETH Zürich , 8093 Zürich, SwitzerlandDepartment of Physics, Autonomous University of Barcelona , Cerdanyola del Vallès, Spain; European Organization for Nuclear Research (CERN) , Geneva 1211, SwitzerlandEuropean Organization for Nuclear Research (CERN) , Geneva 1211, SwitzerlandEuropean Organization for Nuclear Research (CERN) , Geneva 1211, SwitzerlandEuropean Organization for Nuclear Research (CERN) , Geneva 1211, SwitzerlandIBM Quantum, IBM Research Europe - Zurich , Rüschlikon 8803, SwitzerlandIBM Quantum, IBM Research Europe - Zurich , Rüschlikon 8803, SwitzerlandIBM Quantum, IBM Research Europe - Zurich , Rüschlikon 8803, SwitzerlandMuch hope for finding new physics phenomena at microscopic scale relies on the observations obtained from High Energy Physics experiments, like the ones performed at the Large Hadron Collider (LHC). However, current experiments do not indicate clear signs of new physics that could guide the development of additional Beyond Standard Model (BSM) theories. Identifying signatures of new physics out of the enormous amount of data produced at the LHC falls into the class of anomaly detection and constitutes one of the greatest computational challenges. In this article, we propose a novel strategy to perform anomaly detection in a supervised learning setting, based on the artificial creation of anomalies through a random process. For the resulting supervised learning problem, we successfully apply classical and quantum support vector classifiers (CSVC and QSVC respectively) to identify the artificial anomalies among the SM events. Even more promising, we find that employing an SVC trained to identify the artificial anomalies, it is possible to identify realistic BSM events with high accuracy. In parallel, we also explore the potential of quantum algorithms for improving the classification accuracy and provide plausible conditions for the best exploitation of this novel computational paradigm.https://doi.org/10.1088/2632-2153/ad07f7high energy physicsanomaly detectionquantum computingquantum machine learning |
| spellingShingle | Julian Schuhmacher Laura Boggia Vasilis Belis Ema Puljak Michele Grossi Maurizio Pierini Sofia Vallecorsa Francesco Tacchino Panagiotis Barkoutsos Ivano Tavernelli Unravelling physics beyond the standard model with classical and quantum anomaly detection Machine Learning: Science and Technology high energy physics anomaly detection quantum computing quantum machine learning |
| title | Unravelling physics beyond the standard model with classical and quantum anomaly detection |
| title_full | Unravelling physics beyond the standard model with classical and quantum anomaly detection |
| title_fullStr | Unravelling physics beyond the standard model with classical and quantum anomaly detection |
| title_full_unstemmed | Unravelling physics beyond the standard model with classical and quantum anomaly detection |
| title_short | Unravelling physics beyond the standard model with classical and quantum anomaly detection |
| title_sort | unravelling physics beyond the standard model with classical and quantum anomaly detection |
| topic | high energy physics anomaly detection quantum computing quantum machine learning |
| url | https://doi.org/10.1088/2632-2153/ad07f7 |
| work_keys_str_mv | AT julianschuhmacher unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT lauraboggia unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT vasilisbelis unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT emapuljak unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT michelegrossi unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT mauriziopierini unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT sofiavallecorsa unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT francescotacchino unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT panagiotisbarkoutsos unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection AT ivanotavernelli unravellingphysicsbeyondthestandardmodelwithclassicalandquantumanomalydetection |