Boosted decision trees in the era of new physics: a smuon analysis case study

Abstract

Machine learning algorithms are growing increasingly popular in particle physics analyses, where they are used for their ability to solve difficult classification and regression problems. While the tools are very powerful, they may often be under- or mis-utilised. In the following, we investigate the use of gradient boosting techniques as applicable to a generic particle physics problem. We use as an example a Beyond the Standard Model smuon collider analysis which applies to both current and future hadron colliders, and we compare our results to a traditional cut-and-count approach. In particular, we interrogate the use of metrics in imbalanced datasets which are characteristic of high energy physics problems, offering an alternative to the widely used area under the curve (auc) metric through a novel use of the F-score metric. We present an in-depth comparison of feature selection and investigation using a principal component analysis, Shapley values, and feature permutation methods in a way which we hope will be widely applicable to future particle physics analyses. Moreover, we show that a machine learning model can extend the 95% confidence level exclusions obtained in a traditional cut-and-count analysis, while potentially bypassing the need for complicated feature selections. Finally, we discuss the possibility of constructing a general machine learning model which is applicable to probe a two-dimensional mass plane.

35 pages, 7 images

References in corpus (15)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction
• Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• QCD radiation in the production of heavy colored particles at the LHC
• Minimal Kinematic Constraints and MT2
• Evidence for production of single top quarks and first direct measurement of |Vtb|
• Observation of Single Top Quark Production and Measurement of |Vtb| with CDF
• Search for supersymmetry in final states with two oppositely charged same-flavor leptons and missing transverse momentum in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms
• Threshold Resummation for Slepton-Pair Production at Hadron Colliders
• Studies of Boosted Decision Trees for MiniBooNE Particle Identification
• Modern Machine Learning and Particle Physics
• Resonance Searches with Machine Learned Likelihood Ratios
• Extracting more from boosted decision trees: A high energy physics case study

Cited by in corpus (17)

• Searches for the BSM scenarios at the LHC using decision tree based machine learning algorithms: A comparative study and review of Random Forest, Adaboost, XGboost and LightGBM frameworks
• Machine learning the trilinear and light-quark Yukawa couplings from Higgs pair kinematic shapes
• Learning to Identify Semi-Visible Jets
• Improving sensitivity of trilinear RPV SUSY searches using machine learning at the LHC
• Beyond Cuts in Small Signal Scenarios -- Enhanced Sneutrino Detectability Using Machine Learning
• Using Machine Learning to Improve Neutron Identification in Water Cherenkov Detectors
• Boosted top tagging and its interpretation using Shapley values
• Slepton searches in the trilinear RPV SUSY scenarios at the HL-LHC and HE-LHC
• Extracting Higgs Self-Coupling Constraints through Triple Higgs Boson Production at Future Hadron Colliders
• Optimal sensitivity of anomalous charged triple gauge couplings through $W$ boson helicity at the $e^{+}{e}^{-}$ colliders
• Higgs couplings in SMEFT via Zh production at the HL-LHC
• Prospects for exotic $h\to 4\tau$ decays in single and di-Higgs boson production at the LHC and future hadron colliders
• Improving smuon searches with Neural Networks
• Searching for top-philic heavy resonances in boosted four-top final states
• Moiré Topology in Twisted Structures with Noncollinear Spin-Orbit Coupling
• The Physics Behind ML-based Quark-Gluon Taggers
• How to use Machine Learning to improve the discrimination between signal and background at particle colliders