Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
Аутори
Sirunyan, A. M.Tumasyan, A.
Adam, W.
Ambrogi, F.
Bergauer, T.
Adžić, Petar
Ćirković, Predrag
Đorđević, Miloš
Milenović, Predrag
Milošević, Jovan
Stojanović, Milan
Остала ауторства
CMS CollaborationЧланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
Извор:
Journal of Instrumentation, 2020Напомена:
- CMS Collaboration (ukupan broj autora: 2304)
DOI: 10.1088/1748-0221/15/06/P06005
ISSN: 1748-0221
WoS: 000545350900005
Scopus: 2-s2.0-85088524436
Колекције
Институција/група
VinčaTY - JOUR AU - Sirunyan, A. M. AU - Tumasyan, A. AU - Adam, W. AU - Ambrogi, F. AU - Bergauer, T. AU - Adžić, Petar AU - Ćirković, Predrag AU - Đorđević, Miloš AU - Milenović, Predrag AU - Milošević, Jovan AU - Stojanović, Milan PY - 2020 UR - https://vinar.vin.bg.ac.rs/handle/123456789/9096 AB - Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency. T2 - Journal of Instrumentation T1 - Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques DO - 10.1088/1748-0221/15/06/P06005 ER -
@article{ author = "Sirunyan, A. M. and Tumasyan, A. and Adam, W. and Ambrogi, F. and Bergauer, T. and Adžić, Petar and Ćirković, Predrag and Đorđević, Miloš and Milenović, Predrag and Milošević, Jovan and Stojanović, Milan", year = "2020", abstract = "Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.", journal = "Journal of Instrumentation", title = "Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques", doi = "10.1088/1748-0221/15/06/P06005" }
Sirunyan, A. M., Tumasyan, A., Adam, W., Ambrogi, F., Bergauer, T., Adžić, P., Ćirković, P., Đorđević, M., Milenović, P., Milošević, J.,& Stojanović, M.. (2020). Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques. in Journal of Instrumentation. https://doi.org/10.1088/1748-0221/15/06/P06005
Sirunyan AM, Tumasyan A, Adam W, Ambrogi F, Bergauer T, Adžić P, Ćirković P, Đorđević M, Milenović P, Milošević J, Stojanović M. Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques. in Journal of Instrumentation. 2020;. doi:10.1088/1748-0221/15/06/P06005 .
Sirunyan, A. M., Tumasyan, A., Adam, W., Ambrogi, F., Bergauer, T., Adžić, Petar, Ćirković, Predrag, Đorđević, Miloš, Milenović, Predrag, Milošević, Jovan, Stojanović, Milan, "Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques" in Journal of Instrumentation (2020), https://doi.org/10.1088/1748-0221/15/06/P06005 . .