Reports of My Demise Are Greatly Exaggerated: -subjettiness Taggers Take On Jet Images
arXiv:1807.04769 · doi:10.21468/SciPostPhys.7.3.036
Abstract
We compare the performance of a convolutional neural network (CNN) trained on jet images with dense neural networks (DNNs) trained on n-subjettiness variables to study the distinguishing power of these two separate techniques applied to top quark decays. We find that they perform almost identically and are highly correlated once jet mass information is included, which suggests they are accessing the same underlying information which can be intuitively understood as being contained in 4-, 5-, 6-, and 8-body kinematic phase spaces depending on the sample. This suggests both of these methods are highly useful for heavy object tagging and provides a tentative answer to the question of what the image network is actually learning.
arXiv comment15 pages, 9 figures, resubmitted as part of scipost review process
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
- The anti-k_t jet clustering algorithm
- An Introduction to PYTHIA 8.2
- FastJet user manual
- MadGraph 5 : Going Beyond
- Parton distributions with LHC data
- LHAPDF6: parton density access in the LHC precision era
- Successive Combination Jet Algorithm For Hadron Collisions
- Jet substructure as a new Higgs search channel at the LHC
- Identifying Boosted Objects with N-subjettiness
- Rivet user manual
- A standard format for Les Houches Event Files
- Top-tagging: A Method for Identifying Boosted Hadronic Tops
- N-Jettiness: An Inclusive Event Shape to Veto Jets
- Energy Correlation Functions for Jet Substructure
- Maximizing Boosted Top Identification by Minimizing N-subjettiness
- Fat Jets for a Light Higgs
- Stop Reconstruction with Tagged Tops
- Deep learning in color: towards automated quark/gluon jet discrimination
- Jet-Images -- Deep Learning Edition
- Deep-learning Top Taggers or The End of QCD?
- Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
- Boosted objects and jet substructure at the LHC
- Deep-learned Top Tagging with a Lorentz Layer
- Jet mass and substructure of inclusive jets in sqrt(s) = 7 TeV pp collisions with the ATLAS experiment
- New Angles on Energy Correlation Functions
- Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
- A generic anti-QCD jet tagger
- Evidence for the decay with the ATLAS detector
- Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
- Energy flow polynomials: A complete linear basis for jet substructure
- Finding top quarks with shower deconstruction
- Finding physics signals with shower deconstruction
- Pulling Out All the Tops with Computer Vision and Deep Learning
- How Much Information is in a Jet?
- Novel Jet Observables from Machine Learning
Cited by in corpus (26)
- Robust Independent Validation of Experiment and Theory: Rivet version 3
- Performance of top-quark and -boson tagging with ATLAS in Run 2 of the LHC
- DisCo Fever: Robust Networks Through Distance Correlation
- ABCDisCo: Automating the ABCD Method with Machine Learning
- Deep-Learning Jets with Uncertainties and More
- 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
- Mapping Machine-Learned Physics into a Human-Readable Space
- Per-Object Systematics using Deep-Learned Calibration
- Topological Obstructions to Autoencoding
- Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
- Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
- CapsNets Continuing the Convolutional Quest
- A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
- A Lorentz-Equivariant Transformer for All of the LHC
- Resolving Extreme Jet Substructure
- Exploring Jet Substructure in Semi-visible jets
- Dynamic Radius Jet Clustering Algorithm
- Jet tagging made easy
- Pileup and Infrared Radiation Annihilation (PIRANHA): A Paradigm for Continuous Jet Grooming
- Jet Classification Using High-Level Features from Anatomy of Top Jets
- Boosted top tagging and its interpretation using Shapley values
- Top-philic Machine Learning
- Foundations of automatic feature extraction at LHC--point clouds and graphs
- Tagging ultra-boosted jets at FCC-hh using machine learning techniques
- Power Counting Energy Flow Polynomials