2016/12/31 by A. Alves, Alexandre Alves · 27 citations
Computer Science · Physics and Astronomy · #Artificial neural network #Boson #Computational Physics and Python Applications #Higgs boson #High-Energy Particle Collisions Research #Large Hadron Collider #Lepton #Particle physics theoretical and experimental studies #Scalability #Support vector machine #Task (project management) #cs.LG #hep-ph #physics.data-an
paper · pdf · doi:10.1088/1748-0221/12/05/t05005
published in Journal of Instrumentation 12(05), T05005 (Institute of Physics) · 20 pages, 4 figures, 3 tables. Version published in the Journal of Instrumentation
openalex created_date 2017/01/06 · arxiv created 2017/05/30 · openalex publication_date 2017/05/30 · arxiv updated 2017/06/01 · openalex updated_date 2026/08/06
Machine learning (ML) algorithms have been employed in the problem of classifying signal and background events with high accuracy in particle physics. In this paper, we compare the performance of a widespread ML technique, namely, stacked generalization , against the results of two state-of-art algorithms: (1) a deep neural network (DNN) in the task of discovering a new neutral Higgs boson and (2) a scalable machine learning system for tree boosting, in the Standard Model Higgs to tau leptons channel, both at the 8 TeV LHC. In a cut-and-count analysis, stacking three algorithms performed around 16% worse than DNN but demanding far less computation efforts, however, the same stacking outperforms boosted decision trees. Using the stacked classifiers in a multivariate statistical analysis (MVA), on the other hand, significantly enhances the statistical significance compared to cut-and-count in both Higgs processes, suggesting that combining an ensemble of simpler and faster ML algorithms with MVA tools is a better approach than building a complex state-of-art algorithm for cut-and-count.