Unsupervised Outlier Detection in Heavy-Ion Collisions

Abstract

We present different methods of unsupervised learning which can be used for outlier detection in high energy nuclear collisions. The UrQMD model is used to generate the bulk background of events as well as different variants of outlier events which may result from misidentified centrality or detector malfunctions. The methods presented here can be generalized to different and novel physics effects. To detect the outliers, dimensional reduction algorithms are implemented, specifically the Principle Component Analysis (PCA) and Autoencoders (AEN). We find that mainly the reconstruction error is a good measure to distinguish outliers from background. The performance of the algorithms is compared using a ROC curve. It is shown that the number of reduced (encoded) dimensions to describe a single event contributes significantly to the performance of the outlier detection task. We find that the model which is best suited to separate outlier events requires a good performance in reconstructing events and at the same time a small number of parameters.

arXiv comment24 pages, 12 figures, new version with added references in section 1 and slightly improved layout of some figures

References in corpus (27)

• Microscopic Models for Ultrarelativistic Heavy Ion Collisions
• Relativistic Hadron-Hadron Collisions in the Ultra-Relativistic Quantum Molecular Dynamics Model (UrQMD)
• A high-bias, low-variance introduction to Machine Learning for physicists
• Energy Dependence of Moments of Net-proton Multiplicity Distributions at RHIC
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Searching for New Physics with Deep Autoencoders
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• The Machine Learning Landscape of Top Taggers
• QCD or What?
• Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
• Machine and Deep Learning Applications in Particle Physics
• JEDI-net: a jet identification algorithm based on interaction networks
• Regressive and generative neural networks for scalar field theory
• Dynamical net-proton fluctuations near a QCD critical point
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• A machine learning study to identify spinodal clumping in high energy nuclear collisions
• Towards Machine Learning Analytics for Jet Substructure
• Large proton cumulants from the superposition of ordinary multiplicity distributions
• Entropy production and reheating at the chiral phase transition
• Broadening of the chiral critical region in a hydrodynamically expanding medium
• Influence of an inhomogeneous and expanding medium on signals of the QCD phase transition
• Probing heavy ion collisions using quark and gluon jet substructure with machine learning

Cited by in corpus (21)

• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Better Latent Spaces for Better Autoencoders
• Exploring QCD matter in extreme conditions with Machine Learning
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Reconstructing spectral functions via automatic differentiation
• What's Anomalous in LHC Jets?
• Anomaly Detection under Coordinate Transformations
• An equation-of-state-meter for CBM using PointNet
• Digital Twins and Civil Engineering Phases: Reorienting Adoption Strategies
• Non-resonant Anomaly Detection with Background Extrapolation
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning
• Preserving New Physics while Simultaneously Unfolding All Observables
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure
• Cold-Atom Buoy: A Differential Magnetic Sensing Technique in Cold Quadrupole Traps