DOE OSTI · 3011763
Identification of tau leptons using a convolutional neural network with domain adaptation
Abstract
A tau lepton identification algorithm,DeepTau, based on convolutional neural network techniques, has been developed in the CMS experiment to discriminate reconstructed hadronic decays of tau leptons (τ h ) from quark or gluon jets and electrons and muons that are misreconstructed as τ h candidates. The latest version of this algorithm, v2.5, includes domain adaptation by backpropagation, a technique that reduces discrepancies between collision data and simulation in the region with the highest purity of genuine τh candidates. Additionally, a refined training workflow improves classification performance with respect to the previous version of the algorithm, with a reduction of 30–50% in the probability for quark and gluon jets to be misidentified as τ h candidates for given reconstruction and identification efficiencies. This paper presents the novel improvements introduced in theDeepTau algorithm and evaluates its performance in LHC proton-proton collision data at √(s) = 13 and 13.6 TeV collected in 2018 and 2022 with integrated luminosities of 60 and 35 fb -1 , respectively. Techniques to calibrate the performance of the τ h identification algorithm in simulation with respect to its measured performance in real data are presented, together with a subset of results among those measured for use in CMS physics analyses.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Hayrapetyan, Aram [Yerevan Physics Inst. (YerPhI) (Armenia); CMS Collaboration. et al.], Makarenko, V. (ORCID:0000000284068605), Tumasyan, A. (ORCID:0009000006846742), Adam, W. (ORCID:0000000190994341), Andrejkovic, J.W., Benato, L. (ORCID:0000000151357489), Bergauer, T. (ORCID:0000000257860293), Dragicevic, M. (ORCID:0000000319676783), Giordano, C., Hussain, P.S. (ORCID:0000000248255278), Jeitler, M. (ORCID:0000000251419560), Krammer, N. (ORCID:0000000205480985), Li, A. (ORCID:000000024547116X), Liko, D. (ORCID:000000023380473X), Matthewman, M., Mikulec, I. (ORCID:0000000303852746), Schieck, J. (ORCID:0000000210588093), Schöfbeck, R. (ORCID:0000000223328784), Schwarz, D. (ORCID:0000000238217331), Shooshtari, M. (ORCID:0009000488824887), Sonawane, M. (ORCID:0000000305107010), Waltenberger, W. (ORCID:0000000262157228), Wulz, C.-E. (ORCID:0000000192265812), Janssen, T. (ORCID:0000000239984081), Kwon, H. (ORCID:0009000251655018), Ocampo Henao, D. (ORCID:0000000197593452), Van Laer, T. (ORCID:0000000177762108), Van Mechelen, P. (ORCID:0000000287319051), Bierkens, J. (ORCID:0000000208753977), Breugelmans, N., D'Hondt, J. (ORCID:0000000295986241), Dansana, S. (ORCID:0000000277527471), De Moor, A. (ORCID:0000000159641935), Delcourt, M. (ORCID:0000000182061787), Heyen, F., Hong, Y. (ORCID:0000000347522458), Kashko, P. (ORCID:0000000270507152), Lowette, S. (ORCID:0000000339849987), Makarenko, I. (ORCID:0000000285534508), Müller, D. (ORCID:0000000217524527), Song, J. (ORCID:0000000327315881), Tavernier, S. (ORCID:0000000267929522), Tytgat, M. (ORCID:0000000239902074), Van Onsem, G.P. (ORCID:0000000216642337), Van Putte, S. (ORCID:0000000315593606), Vannerom, D. (ORCID:0000000227475095), Bilin, B. (ORCID:0000000314397128), Clerbaux, B. (ORCID:0000000185478211), Das, A.K., De Bruyn, I. (ORCID:0000000317044360), De Lentdecker, G. (ORCID:0000000151247693), Evard, H. (ORCID:0009000550391462), Favart, L. (ORCID:0000000316457454), Gianneios, P. (ORCID:0009000372330738), Khalilzadeh, A., Khan, F.A. (ORCID:000900022039277X), Malara, A. (ORCID:0000000186459282), Shahzad, M.A., Thomas, L. (ORCID:0000000227563853), Vanden Bemden, M. (ORCID:0009000077257945), Vander Velde, C. (ORCID:0000000333927294), Vanlaer, P. (ORCID:0000000279314496), Zhang, F. (ORCID:0000000261582468), De Coen, M. (ORCID:0000000258547442), Dobur, D. (ORCID:0000000300124866), Gokbulut, G. (ORCID:0000000201756454), Knolle, J. (ORCID:0000000247815704), Lambrecht, L. (ORCID:0000000191081560), Marckx, D. (ORCID:0000000167522290), Skovpen, K. (ORCID:0000000211600621), Van Den Bossche, N. (ORCID:0000000329734991), van der Linden, J. (ORCID:000000027174781X), Vandenbroeck, J. (ORCID:0009000461413404), Wezenbeek, L. (ORCID:000000016952891X), Bein, S. (ORCID:0000000193877407), Benecke, A. (ORCID:0000000302523609), Bethani, A. (ORCID:0000000281507043), Bruno, G. (ORCID:0000000188578197), Cappati, A. (ORCID:0000000343860564), De Favereau De Jeneret, J. (ORCID:0000000317758574), Delaere, C. (ORCID:0000000187076021), Giammanco, A. (ORCID:0000000196408294), Guzel, A.O. (ORCID:0000000294045933), Lemaitre, V., Lidrych, J. (ORCID:0000000314390196), Malek, P. (ORCID:0000000331839741), Mastrapasqua, P. (ORCID:0000000220432367), Turkcapar, S. (ORCID:0000000326080494), Alves, G.A. (ORCID:0000000283691446), Barroso Ferreira Filho, M. (ORCID:0000000339040571), Coelho, E. (ORCID:0000000161149907), Hensel, C. (ORCID:0000000188747624), Menezes De Oliveira, T. (ORCID:0009000947298354), Mora Herrera, C. (ORCID:0000000339153170), Rebello Teles, P. (ORCID:0000000190298506), Soeiro, M. (ORCID:0000000247676468), Tonelli Manganote, E.J. (ORCID:0000000324598521), Vilela Pereira, A. (ORCID:0000000331774626), Aldá Júnior, W.L. (ORCID:0000000158559817), Brandao Malbouisson, H. (ORCID:000000021326318X). 2025-12-19. Identification of tau leptons using a convolutional neural network with domain adaptation. https://doi.org/10.1088/1748-0221%2F20%2F12%2Fp12032
Cite the original work for its findings. Save a collection to share your selection of sources.