Meta-learning and data augmentation for mass-generalised jet taggers
arXiv:2111.06047 · doi:10.1103/PhysRevD.105.094030
Abstract
Deep neural networks trained for jet tagging are typically specific to a narrow range of transverse momenta or jet masses. Given the large phase space that the LHC is able to probe, the potential benefit of classifiers that are effective over a wide range of masses or transverse momenta is significant. In this work we benchmark the performance of a number of methods for achieving accurate classification at masses distant from those used in training, with a focus on algorithms that leverage meta-learning. We study the discrimination of jets from boosted bosons against a QCD background. We find that a simple data augmentation strategy that standardises the angular scale of jets with different masses is sufficient to produce strong generalisation. The meta-learning algorithms provide only a small improvement in generalisation when combined with this augmentation. We also comment on the relationship between mass generalisation and mass decorrelation, demonstrating that those models which generalise better than the baseline also sculpt the background to a smaller degree.
arXiv comment12 pages, 5 figures, v2: Table 1 revised
References in corpus (36)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- An Introduction to PYTHIA 8.2
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- FeynRules 2.0 - A complete toolbox for tree-level phenomenology
- Machine learning and the physical sciences
- Combined results of searches for the standard model Higgs boson in pp collisions at sqrt(s) = 7 TeV
- 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
- Jet-Images -- Deep Learning Edition
- Evidence for a particle produced in association with weak bosons and decaying to a bottom-antibottom quark pair in Higgs boson searches at the Tevatron
- Energy Flow Networks: Deep Sets for Particle Jets
- Parameterized Machine Learning for High-Energy Physics
- QCD or What?
- What is the Machine Learning?
- Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
- Machine and Deep Learning Applications in Particle Physics
- Dijet resonance search with weak supervision using TeV collisions in the ATLAS detector
- Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
- Scale-invariant resonance tagging in multijet events and new physics in Higgs pair production
- Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
- DisCo Fever: Robust Networks Through Distance Correlation
- Machine Learning Uncertainties with Adversarial Neural Networks
- Modern Machine Learning and Particle Physics
- Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
- uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
- Mass Unspecific Supervised Tagging (MUST) for boosted jets
- Equivariant Energy Flow Networks for Jet Tagging
- A multi-dimensional search for new heavy resonances decaying to boosted WW, WZ, or ZZ boson pairs in the dijet final state at 13 TeV
- Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
- Inclusive search for highly boosted Higgs bosons decaying to bottom quark-antiquark pairs in proton-proton collisions at 13 TeV
- Mass Agnostic Jet Taggers
- Search for non-resonant Higgs boson pair production in the final state with the ATLAS detector in collisions at TeV
- Search for Higgs boson decays into a boson and a light hadronically decaying resonance using 13 TeV collision data from the ATLAS detector
- Anomaly detection from mass unspecific jet tagging
- Enhancing searches for resonances with machine learning and moment decomposition
- New approaches for boosting to uniformity