Improving the performance of weak supervision searches using transfer and meta-learning

被引:9
作者
Beauchesne, Hugues [1 ]
Chen, Zong-En [2 ,3 ]
Chiang, Cheng-Wei [1 ,2 ,3 ]
机构
[1] Natl Ctr Theoret Sci, Phys Div, Taipei 10617, Taiwan
[2] Natl Taiwan Univ, Dept Phys, Taipei 10617, Taiwan
[3] Natl Taiwan Univ, Ctr Theoret Phys, Taipei 10617, Taiwan
关键词
New Gauge Interactions; Specific BSM Phenomenology;
D O I
10.1007/JHEP02(2024)138
中图分类号
O412 [相对论、场论]; O572.2 [粒子物理学];
学科分类号
摘要
Weak supervision searches have in principle the advantages of both being able to train on experimental data and being able to learn distinctive signal properties. However, the practical applicability of such searches is limited by the fact that successfully training a neural network via weak supervision can require a large amount of signal. In this work, we seek to create neural networks that can learn from less experimental signal by using transfer and meta-learning. The general idea is to first train a neural network on simulations, thereby learning concepts that can be reused or becoming a more efficient learner. The neural network would then be trained on experimental data and should require less signal because of its previous training. We find that transfer and meta-learning can substantially improve the performance of weak supervision searches.
引用
收藏
页数:19
相关论文
共 46 条
[1]   Dijet Resonance Search with Weak Supervision Using √S=13 TeV pp Collisions in the ATLAS Detector [J].
Aad, G. ;
Abbott, B. ;
Abbott, D. C. ;
Abud, A. Abed ;
Abeling, K. ;
Abhayasinghe, D. K. ;
Abidi, S. H. ;
AbouZeid, O. S. ;
Abraham, N. L. ;
Abramowicz, H. ;
Abreu, H. ;
Abulaiti, Y. ;
Acharya, B. S. ;
Achkar, B. ;
Adam, L. ;
Bourdarios, C. Adam ;
Adamczyk, L. ;
Adamek, L. ;
Adelman, J. ;
Adersberger, M. ;
Adiguzel, A. ;
Adorni, S. ;
Adye, T. ;
Affolder, A. A. ;
Afik, Y. ;
Agapopoulou, C. ;
Agaras, M. N. ;
Aggarwal, A. ;
Agheorghiesei, C. ;
Aguilar-Saavedra, J. A. ;
Ahmad, A. ;
Ahmadov, F. ;
Ahmed, W. S. ;
Ai, X. ;
Aielli, G. ;
Akatsuka, S. ;
Akesson, T. P. A. ;
Akilli, E. ;
Akimov, A., V ;
Al Khoury, K. ;
Alberghi, G. L. ;
Albert, J. ;
Verzini, M. J. Alconada ;
Alderweireldt, S. ;
Aleksa, M. ;
Aleksandrov, I. N. ;
Alexa, C. ;
Alexopoulos, T. ;
Alfonsi, A. ;
Alfonsi, F. .
PHYSICAL REVIEW LETTERS, 2020, 125 (13)
[2]  
Abadi M., 2015, arXiv, DOI [10.48550/arXiv.1603.04467, DOI 10.48550/ARXIV.1603.04467]
[3]   Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report [J].
Albouy, Guillaume ;
Barron, Jared ;
Beauchesne, Hugues ;
Bernreuther, Elias ;
Bona, Marcella ;
Cazzaniga, Cesare ;
Cesarotti, Cari ;
Cohen, Timothy ;
de Cosa, Annapaola ;
Curtin, David ;
Demiragli, Zeynep ;
Doglioni, Caterina ;
Elliot, Alison ;
DiPetrillo, Karri Folan ;
Eble, Florian ;
Erice, Carlos ;
Freer, Chad ;
Garcia-Bellido, Aran ;
Gemmell, Caleb ;
Genest, Marie-Helene ;
di Cortona, Giovanni Grilli ;
Gustavino, Giuliano ;
Hemme, Nicoline ;
Holmes, Tova ;
Kar, Deepak ;
Knapen, Simon ;
Kulkarni, Suchita ;
Lavezzo, Luca ;
Lowette, Steven ;
Maier, Benedikt ;
Mee, Sean ;
Mrenna, Stephen ;
Nair, Harikrishnan ;
Niedziela, Jeremi ;
Papageorgakis, Christos ;
Parmar, Nukulsinh ;
Paus, Christoph ;
Pedro, Kevin ;
Peixoto, Ana ;
Perloff, Alexx ;
Plehn, Tilman ;
Scherb, Christiane ;
Schwaller, Pedro ;
Shelton, Jessie ;
Singh, Akanksha ;
Sinha, Sukanya ;
Sjostrand, Torbjorn ;
Spourdalakis, Aris G. B. ;
Stolarski, Daniel ;
Strassler, Matthew J. .
EUROPEAN PHYSICAL JOURNAL C, 2022, 82 (12)
[4]   The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations [J].
Alwall, J. ;
Frederix, R. ;
Frixione, S. ;
Hirschi, V. ;
Maltoni, F. ;
Mattelaer, O. ;
Shao, H. -S. ;
Stelzer, T. ;
Torrielli, P. ;
Zaro, M. .
JOURNAL OF HIGH ENERGY PHYSICS, 2014, (07)
[5]   Simulation assisted likelihood-free anomaly detection [J].
Andreassen, Anders ;
Nachman, Benjamin ;
Shih, David .
PHYSICAL REVIEW D, 2020, 101 (09)
[6]  
ATLAS collaboration, 2024, Phys. Lett. B, V848
[7]   Parton distributions with LHC data [J].
Ball, Richard D. ;
Bertone, Valerio ;
Carrazza, Stefano ;
Deans, Christopher S. ;
Del Debbio, Luigi ;
Forte, Stefano ;
Guffanti, Alberto ;
Hartland, Nathan P. ;
Latorre, Jose I. ;
Rojo, Juan ;
Ubiali, Maria .
NUCLEAR PHYSICS B, 2013, 867 (02) :244-289
[8]   Searching for dark jets with displaced vertices using weakly supervised machine learning [J].
Bardhan, Debjyoti ;
Kats, Yevgeny ;
Wunch, Noam .
PHYSICAL REVIEW D, 2023, 108 (03)
[9]   Topological obstructions to autoencoding [J].
Batson, Joshua ;
Haaf, C. Grace ;
Kahn, Yonatan ;
Roberts, Daniel A. .
JOURNAL OF HIGH ENERGY PHYSICS, 2021, 2021 (04)
[10]   Classification of dark pion multiplets as dark matter candidates and collider phenomenology [J].
Beauchesne, Hugues ;
di Cortona, Giovanni Grilli .
JOURNAL OF HIGH ENERGY PHYSICS, 2020, 2020 (02)