Binary JUNIPR: an interpretable probabilistic model for discrimination
arXiv:1906.10137 · doi:10.1103/PhysRevLett.123.182001
Abstract
JUNIPR is an approach to unsupervised learning in particle physics that scaffolds a probabilistic model for jets around their representation as binary trees. Separate JUNIPR models can be learned for different event or jet types, then compared and explored for physical insight. The relative probabilities can also be used for discrimination. In this paper, we show how the training of the separate models can be refined in the context of classification to optimize discrimination power. We refer to this refined approach as Binary JUNIPR. Binary JUNIPR achieves state-of-the-art performance for quark/gluon discrimination and top-tagging. The trained models can then be analyzed to provide physical insight into how the classification is achieved. As examples, we explore differences between quark and gluon jets and between gluon jets generated with two different simulations.
arXiv comment6 pages, 3 figures
References in corpus (33)
- Adam: A Method for Stochastic Optimization
- Successive Combination Jet Algorithm For Hadron Collisions
- Better Jet Clustering Algorithms
- Top-tagging: A Method for Identifying Boosted Hadronic Tops
- ParticleNet: Jet Tagging via Particle Clouds
- CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
- Classification without labels: Learning from mixed samples in high energy physics
- Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
- Deep learning in color: towards automated quark/gluon jet discrimination
- Jet-Images -- Deep Learning Edition
- Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
- Deep-learning Top Taggers or The End of QCD?
- Searching for New Physics with Deep Autoencoders
- Anomaly Detection for Resonant New Physics with Machine Learning
- Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
- Energy Flow Networks: Deep Sets for Particle Jets
- The Machine Learning Landscape of Top Taggers
- Quark and Gluon Tagging at the LHC
- Deep-learned Top Tagging with a Lorentz Layer
- Systematics of quark/gluon tagging
- Quark and Gluon Jet Substructure
- Adversarially-trained autoencoders for robust unsupervised new physics searches
- Pulling Out All the Tops with Computer Vision and Deep Learning
- Light-quark and gluon jet discrimination in pp collisions at = 7 TeV with the ATLAS detector
- QCD-Aware Recursive Neural Networks for Jet Physics
- Pileup Mitigation with Machine Learning (PUMML)
- JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
- Learning to Classify from Impure Samples with High-Dimensional Data
- Multivariate discrimination and the Higgs + W/Z search
- Recursive Neural Networks in Quark/Gluon Tagging
- Jet Charge and Machine Learning
- A robust anomaly finder based on autoencoders
- Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
Cited by in corpus (17)
- Anomaly Detection with Density Estimation
- Machine Learning and LHC Event Generation
- Neural Networks for Full Phase-space Reweighting and Parameter Tuning
- Modern Machine Learning and Particle Physics
- A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
- A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
- Casting a graph net to catch dark showers
- Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
- Learning the language of QCD jets with transformers
- Explainable machine learning of the underlying physics of high-energy particle collisions
- Constraints on the trilinear and quartic Higgs couplings from triple Higgs production at the LHC and beyond
- Exploring Jet Substructure in Semi-visible jets
- Parameter Inference from Event Ensembles and the Top-Quark Mass
- Deep Learning Jet Substructure from Two-Particle Correlation
- Sequence-based Machine Learning Models in Jet Physics
- Extrapolating Jet Radiation with Autoregressive Transformers
- Observable Optimization for Precision Theory: Machine Learning Energy Correlators