Interpretable Machine Learning Methods Applied to Jet Background Subtraction in Heavy Ion Collisions
arXiv:2303.08275 · doi:10.1103/PhysRevC.108.L021901
Abstract
Jet measurements in heavy ion collisions can provide constraints on the properties of the quark gluon plasma, but the kinematic reach is limited by a large, fluctuating background. We present a novel application of symbolic regression to extract a functional representation of a deep neural network trained to subtract the background for measurements of jets in relativistic heavy ion collisions. We show that the deep neural network is approximately the same as a method using the particle multiplicity in a jet. This demonstrates that interpretable machine learning methods can provide insight into underlying physical processes.
References in corpus (32)
- A Brief Introduction to PYTHIA 8.1
- FastJet user manual
- Experimental and Theoretical Challenges in the Search for the Quark Gluon Plasma: The STAR Collaboration's Critical Assessment of the Evidence from RHIC Collisions
- Formation of dense partonic matter in relativistic nucleus-nucleus collisions at RHIC: Experimental evaluation by the PHENIX collaboration
- Quark Gluon Plasma an Color Glass Condensate at RHIC? The perspective from the BRAHMS experiment
- The PHOBOS Perspective on Discoveries at RHIC
- Successive Combination Jet Algorithm For Hadron Collisions
- Tuning PYTHIA 8.1: the Monash 2013 Tune
- Pileup subtraction using jet areas
- The Catchment Area of Jets
- Centrality dependence of , K, p production in Pb-Pb collisions at = 2.76 TeV
- Centrality dependence of the charged-particle multiplicity density at mid-rapidity in Pb-Pb collisions at = 2.76 TeV
- Extracting jet transport coefficient from jet quenching at RHIC and LHC
- Jet size dependence of single jet suppression in lead-lead collisions at sqrt(s(NN)) = 2.76 TeV with the ATLAS detector at the LHC
- Review of Jet Measurements in Heavy Ion Collisions
- Measurement of jet fragmentation in PbPb and pp collisions at sqrt(s[NN]) = 2.76 TeV
- Measurement of jet suppression in central Pb-Pb collisions at = 2.76 TeV
- Spectra and ratios of identified particles in Au+Au and d+Au collisions at sqrt(s_NN)=200 GeV
- Determining the jet transport coefficient from inclusive hadron suppression measurements using Bayesian parameter estimation
- Measurement of charged jet suppression in Pb-Pb collisions at TeV
- Measurement of inclusive jet cross sections in pp and PbPb collisions at sqrt(s[NN]) = 2.76 TeV
- Measurement of event background fluctuations for charged particle jet reconstruction in Pb-Pb collisions at TeV
- Measurements of inclusive jet spectra in pp and central Pb-Pb collisions at = 5.02 TeV
- Measurement of jet fragmentation in Pb+Pb and collisions at TeV with the ATLAS detector
- Higher harmonic flow coefficients of identified hadrons in Pb-Pb collisions at = 2.76 TeV
- Measurement of the higher-order anisotropic flow coefficients for identified hadrons in AuAu collisions at = 200 GeV
- Measurement of inclusive charged-particle jet production in Au+Au collisions at =200 GeV
- Charged jet cross sections and properties in proton-proton collisions at TeV
- Machine Learning based jet momentum reconstruction in heavy-ion collisions
- Jet-Underlying Event Separation Method for Heavy Ion Collisions at the Relativistic Heavy Ion Collider
- Measurement of jet-medium interactions via direct photon-hadron correlations in AuAu and Au collisions at GeV
- Model studies of fluctuations in the background for jets in heavy ion collisions
Cited by in corpus (6)
- SymbolFit: Automatic Parametric Modeling with Symbolic Regression
- Boosted top tagging and its interpretation using Shapley values
- Accelerating Graph-based Tracking Tasks with Symbolic Regression
- Jet momentum reconstruction in the QGP background with machine learning
- A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC
- Reconstructing jet anisotropies with cumulants