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

Abstract

Machine learning algorithms are now being extensively used in our daily lives, spanning across diverse industries as well as academia. In the field of high energy physics (HEP), the most common and challenging task is separating a rare signal from a much larger background. The boosted decision tree (BDT) algorithm has been a cornerstone of the high energy physics for analyzing event triggering, particle identification, jet tagging, object reconstruction, event classification, and other related tasks for quite some time. This article presents a comprehensive overview of research conducted by both HEP experimental and phenomenological groups that utilize decision tree algorithms in the context of the Standard Model and Supersymmetry (SUSY). We also summarize the basic concept of machine learning and decision tree algorithm along with the working principle of \texttt{Random Forest}, \texttt{AdaBoost} and two gradient boosting frameworks, such as \texttt{XGBoost}, and \texttt{LightGBM}. Using a case study of electroweakino productions at the high luminosity LHC, we demonstrate how these algorithms lead to improvement in the search sensitivity compared to traditional cut-based methods in both compressed and non-compressed R-parity conserving SUSY scenarios. The effect of different hyperparameters and their optimization, feature importance study using SHapley values are also discussed in detail.

Published in EPJST

References in corpus (112)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Asymptotic formulae for likelihood-based tests of new physics
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• A Comparative Analysis of XGBoost
• Machine learning and the physical sciences
• A Supersymmetry Primer
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• R-parity violating supersymmetry
• Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• Observation of the diphoton decay of the Higgs boson and measurement of its properties
• Deep Learning and its Application to LHC Physics
• ATLAS $b$-jet identification performance and efficiency measurement with $t\bar{t}$ events in $pp$ collisions at $\sqrt{s}=13$ TeV
• Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree
• Deep learning in color: towards automated quark/gluon jet discrimination
• Precision predictions for electroweak superpartner production at hadron colliders with Resummino
• Search for top-squark pair production in the single-lepton final state in pp collisions at sqrt(s) = 8 TeV
• Jet-Images -- Deep Learning Edition
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• New physics explanations of $a_{\mu }$ in light of the FNAL muon $g-2$ measurement
• Jet Flavour Classification Using DeepJet
• The impact of priors and observables on parameter inferences in the Constrained MSSM
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• How to GAN LHC Events
• The post-Higgs MSSM scenario: Habemus MSSM?
• Machine and Deep Learning Applications in Particle Physics
• Search for charged Higgs bosons decaying via $H^{\pm }\to {\tau }^{\pm }{\nu }_{\tau }$ in the $\tau$+jets and $\tau$+lepton final states with 36 fb${}^{-1}$ of $pp$ collision data recorded at $\sqrt{s}=13$ TeV with the ATLAS experiment
• Likelihood Analysis of the pMSSM11 in Light of LHC 13-TeV Data
• Evidence for production of single top quarks
• Dark Matter, Light Stops and Electroweak Baryogenesis
• Evidence for production of single top quarks and first direct measurement of |Vtb|
• Global fits of GUT-scale SUSY models with GAMBIT
• Observation of Single Top Quark Production and Measurement of |Vtb| with CDF
• Search for squarks and gluinos in final states with jets and missing transverse momentum using 139 fb${}^{-1}$ of $\sqrt{s}$ =13 TeV $pp$ collision data with the ATLAS detector
• Search for chargino--neutralino pair production in final states with three leptons and missing transverse momentum in $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• A global fit of the MSSM with GAMBIT
• Search for charged Higgs bosons decaying into top and bottom quarks at $\sqrt{s}$ = 13 TeV with the ATLAS detector
• Search for the Standard Model Higgs boson produced in association with top quarks and decaying into a $b\bar{b}$ pair in $pp$ collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector
• Search for charged Higgs bosons in the H${}^{\pm }$ $\to$ ${\tau }^{\pm }{\nu }_{\tau }$ decay channel in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• LHCb Topological Trigger Reoptimization
• Fast and accurate simulation of particle detectors using generative adversarial networks
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• GUT-inspired SUSY and the muon g-2 anomaly: prospects for LHC 14 TeV
• Supersymmetric Interpretation of the Muon $g-2$ Anomaly
• Neutrino masses in the R-parity violating MSSM
• Studies of Boosted Decision Trees for MiniBooNE Particle Identification
• Evidence for $t\bar{t}t\bar{t}$ production in the multilepton final state in proton-proton collisions at $\sqrt{s}$=13 TeV with the ATLAS detector
• Neutrino masses in R-parity violating supersymmetric models
• Search for charged Higgs bosons decaying into a top and a bottom quark in the all-jet final state of pp collisions at $\sqrt{s}=$ 13 TeV
• Addressing $R_{D^{(\ast )}}$, $R_{K^{(\ast )}}$, muon $g-2$ and ANITA anomalies in a minimal $R$-parity violating supersymmetric framework
• GUT-constrained supersymmetry and dark matter in light of the new $(g-2{)}_{\mu }$ determination
• The BSM-AI project: SUSY-AI - Generalizing LHC limits on Supersymmetry with Machine Learning
• Anomalous muon magnetic moment, supersymmetry, naturalness, LHC search limits and the landscape
• Supervised deep learning in high energy phenomenology: a mini review
• The Electroweak Sector of the pMSSM in the Light of LHC - 8 TeV and Other Data
• Reduced LHC constraints for higgsino-like heavier electroweakinos
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Many faces of low mass neutralino dark matter in the unconstrained MSSM, LHC data and new signals
• Search for new phenomena with top quark pairs in final states with one lepton, jets, and missing transverse momentum in $pp$ collisions at $\sqrt{s}$= 13 TeV with the ATLAS detector
• How light a higgsino or a wino dark matter can become in a compressed scenario of MSSM
• Search for direct pair production of sleptons and charginos decaying to two leptons and neutralinos with mass splittings near the $W$-boson mass in $\sqrt{s}=13$TeV $pp$ collisions with the ATLAS detector
• Search for supersymmetry in events with four or more charged leptons in $139\,\mbox{fb\(^{-1}\)}$ of $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• A Coverage Study of the CMSSM Based on ATLAS Sensitivity Using Fast Neural Networks Techniques
• Scrutinizing $R$-parity violating interactions in light of $R_{K^{(\ast )}}$ data
• Compressed SUSY at 14 TeV LHC
• Boosted decision trees in the era of new physics: a smuon analysis case study
• Muon g-2 and related phenomenology in constrained vector-like extensions of the MSSM
• Constraining the Parameters of High-Dimensional Models with Active Learning
• Low mass neutralino dark matter in mSUGRA and more general models in the light of LHC data
• Non-universal Gaugino mass models under the lamppost of muon (g-2)
• Neutralino dark matter confronted by the LHC constraints on Electroweak SUSY signals
• Status of MSSM Higgs Sector using Global Analysis and Direct Search Bounds, and Future Prospects at the HL-LHC
• B-physics anomalies: The bridge between R-parity violating Supersymmetry and flavoured Dark Matter
• Electron and muon magnetic moments and implications for dark matter and model characterisation in non-universal $U(1{)}^{\prime }$ supersymmetric models
• Revisiting the Exclusion Limits from Direct Chargino-Neutralino Production at the LHC
• Lepton number violating mSUGRA and neutrino masses
• Search for R-parity violating supersymmetry in a final state containing leptons and many jets with the ATLAS experiment using $\sqrt{s}=13$ TeV proton-proton collision data
• Status of low mass LSP in SUSY
• Search for top squarks in final states with two top quarks and several light-flavor jets in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• The ABC of RPV: Classification of R-Parity Violating Signatures at the LHC for Small Couplings
• Supersymmetric gauged U(1)${}_{L_{\mu }-L_{\tau }}$ model for electron and muon $(g-2)$ anomaly
• Fast supersymmetry phenomenology at the Large Hadron Collider using machine learning techniques
• Supersymmetric gauged U(1)${}_{L_{\mu }-L_{\tau }}$ model for neutrinos and the muon $(g-2)$ anomaly
• Machine Learning Templates for QCD Factorization in the Search for Physics Beyond the Standard Model
• A revisit to a compressed supersymmetric spectrum with 125 GeV Higgs
• Probing $(g-2{)}_{\mu }$ at the LHC in the paradigm of R-parity violating MSSM
• Impact of LHC data on muon $g-2$ solutions in vector-like extension of the Constrained MSSM
• Muon and Electron $(g-2)$ Anomalies with Non-Holomorphic Interactions in MSSM
• Constraints from neutrino masses and muon (g-2) in the bilinear R-parity violating supersymmetric model
• Supersymmetric explanation of the muon g-2 anomaly with and without stable neutralino
• Bayesian Neural Networks for Fast SUSY Predictions
• Search for $R$-parity violating supersymmetry in pp collisions at $\sqrt{s}=$ 13 TeV using b jets in a final state with a single lepton, many jets, and high sum of large-radius jet masses
• Updating Bounds on $R$-Parity Violating Supersymmetry from Meson Oscillation Data
• Current status of MSSM Higgs sector with LHC 13 TeV data
• Electroweakino searches at the HL-LHC in the baryon number violating MSSM
• Search for a compressed supersymmetric spectrum with a light Gravitino
• The past, present and future of the heavier electroweakinos in the light of LHC and other data
• Bilinear R-parity violating supersymmetry under the light of neutrino oscillation, higgs and flavor data
• Improving sensitivity of trilinear RPV SUSY searches using machine learning at the LHC
• Indirect Searches of the Degenerate MSSM
• Search for top squarks in the four-body decay mode with single lepton final states in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Beyond Cuts in Small Signal Scenarios -- Enhanced Sneutrino Detectability Using Machine Learning
• Search for resonant production of second-generation sleptons with same-sign dimuon events in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• On Neutrino Masses in the MSSM with BRpV
• Detecting Heavy Higgs Bosons from Natural SUSY at a 100 TeV Hadron Collider

Cited by in corpus (6)

• The ABC of RPV II: Classification of R-parity Violating Signatures from UDD Couplings and their Coverage at the LHC
• Probing sub-TeV Higgsinos aided by a ML-based top tagger in the context of Trilinear RPV SUSY
• Improving smuon searches with Neural Networks
• Projected sensitivity of CTAO to axion-like particles from blazars with a machine learning approach
• The Physics Behind ML-based Quark-Gluon Taggers
• RocketStack: Level-aware Deep Recursive Ensemble Learning Architecture