TopicFlow: Disentangling quark and gluon jets with normalizing flows
arXiv:2211.16053 · doi:10.1103/PhysRevD.107.114003
Abstract
The isolation of pure samples of quark and gluon jets is of key interest at hadron colliders. Recent work has employed topic modeling to disentangle the underlying distributions in mixed samples obtained from experiments. However, current implementations do not scale to high-dimensional observables as they rely on binning the data. In this work we introduce TopicFlow, a method based on normalizing flows to learn quark and gluon jet topic distributions from mixed datasets. These networks are as performant as the histogram-based approach, but since they are unbinned, they are efficient even in high dimension. The models can also be oversampled to alleviate the statistical limitations of histograms. As an example use case, we demonstrate how our models can improve the calibration accuracy of a classifier. Finally, we discuss how the flow likelihoods can be used to perform outlier-robust quark/gluon classification.
arXiv comment10 pages, 5 figures. v2: Added footnote in Section III B. Added baseline and related discussion to Section III C. v3: Match published version
References in corpus (46)
- The anti-k_t jet clustering algorithm
- An Introduction to PYTHIA 8.2
- Normalizing Flows: An Introduction and Review of Current Methods
- Anomaly Detection with Density Estimation
- Classification without labels: Learning from mixed samples in high energy physics
- Deep learning in color: towards automated quark/gluon jet discrimination
- Energy Flow Networks: Deep Sets for Particle Jets
- Quark and Gluon Tagging at the LHC
- Event Generation with Normalizing Flows
- Infrared safe definition of jet flavour
- Systematics of quark/gluon tagging
- Energy flow polynomials: A complete linear basis for jet substructure
- Classifying Anomalies THrough Outer Density Estimation (CATHODE)
- Uncovering latent jet substructure
- i-flow: High-dimensional Integration and Sampling with Normalizing Flows
- Exploring phase space with Neural Importance Sampling
- Invertible Networks or Partons to Detector and Back Again
- On the Topic of Jets: Disentangling Quarks and Gluons at Colliders
- Recursive Neural Networks in Quark/Gluon Tagging
- Quark-Gluon Tagging: Machine Learning vs Detector
- An operational definition of quark and gluon jets
- Targeting Multi-Loop Integrals with Neural Networks
- Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
- Learning the latent structure of collider events
- Mapping Machine-Learned Physics into a Human-Readable Space
- Improving the Simulation of Quark and Gluon Jets with Herwig 7
- A Theory of Quark vs. Gluon Discrimination
- Pure Samples of Quark and Gluon Jets at the LHC
- Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
- Measuring QCD Splittings with Invertible Networks
- Quarks and gluons in the Lund plane
- Properties of jet fragmentation using charged particles measured with the ATLAS detector in collisions at TeV
- A case study of quark-gluon discrimination at NNLL' in comparison to parton showers
- Disentangling Quarks and Gluons with CMS Open Data
- Quark-Gluon Jet Discrimination Using Convolutional Neural Networks
- Investigating the Topology Dependence of Quark and Gluon Jets
- Quenching effects in the cumulative jet spectrum
- Data-driven quark and gluon jet modification in heavy-ion collisions
- SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
- Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
- Learning to Identify Electrons
- Learning to Identify Semi-Visible Jets
- Pure Quark and Gluon Observables in Collinear Drop
- Systematic Quark/Gluon Identification with Ratios of Likelihoods
- Learning to Isolate Muons
- Going off topics to demix quark and gluon jets in extractions