Mapping Machine-Learned Physics into a Human-Readable Space

Abstract

We present a technique for translating a black-box machine-learned classifier operating on a high-dimensional input space into a small set of human-interpretable observables that can be combined to make the same classification decisions. We iteratively select these observables from a large space of high-level discriminants by finding those with the highest decision similarity relative to the black box, quantified via a metric we introduce that evaluates the relative ordering of pairs of inputs. Successive iterations focus only on the subset of input pairs that are misordered by the current set of observables. This method enables simplification of the machine-learning strategy, interpretation of the results in terms of well-understood physical concepts, validation of the physical model, and the potential for new insights into the nature of the problem itself. As a demonstration, we apply our approach to the benchmark task of jet classification in collider physics, where a convolutional neural network acting on calorimeter jet images outperforms a set of six well-known jet substructure observables. Our method maps the convolutional neural network into a set of observables called energy flow polynomials, and it closes the performance gap by identifying a class of observables with an interesting physical interpretation that has been previously overlooked in the jet substructure literature.

arXiv comment20 pages, 7 figures, 3 tables

References in corpus (96)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The anti-k_t jet clustering algorithm
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• MadGraph 5 : Going Beyond
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Jet substructure as a new Higgs search channel at the LHC
• Identifying Boosted Objects with N-subjettiness
• Soft Drop
• Jet Trimming
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Towards an understanding of jet substructure
• Observation of the diphoton decay of the Higgs boson and measurement of its properties
• Top-tagging: A Method for Identifying Boosted Hadronic Tops
• Fast inference of deep neural networks in FPGAs for particle physics
• ParticleNet: Jet Tagging via Particle Clouds
• Energy Correlation Functions for Jet Substructure
• Deep Learning and its Application to LHC Physics
• Maximizing Boosted Top Identification by Minimizing N-subjettiness
• Boosted objects: a probe of beyond the Standard Model physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Recombination Algorithms and Jet Substructure: Pruning as a Tool for Heavy Particle Searches
• Deep Variational Information Bottleneck
• Jet Substructure at the Tevatron and LHC: New results, new tools, new benchmarks
• Jet Substructure at the Large Hadron Collider: Experimental Review
• Classification without labels: Learning from mixed samples in high energy physics
• Stop Reconstruction with Tagged Tops
• Deep learning in color: towards automated quark/gluon jet discrimination
• Principles of general final-state resummation and automated implementation
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• WW scattering at the LHC
• 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
• A Convolutional Neural Network Neutrino Event Classifier
• Substructure of high-p_T Jets at the LHC
• The Machine Learning Landscape of Top Taggers
• Power Counting to Better Jet Observables
• Gaining (Mutual) Information about Quark/Gluon Discrimination
• Boosted objects and jet substructure at the LHC
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• New Angles on Energy Correlation Functions
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Systematics of quark/gluon tagging
• OmniFold: A Method to Simultaneously Unfold All Observables
• Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
• What is the Machine Learning?
• 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
• JEDI-net: a jet identification algorithm based on interaction networks
• Identification techniques for highly boosted W bosons that decay into hadrons
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• Neural Network based Electron Identification in the ZEUS Calorimeter
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• ABCNet: An attention-based method for particle tagging
• Invertible Networks or Partons to Detector and Back Again
• How Much Information is in a Jet?
• Jet Substructure Without Trees
• Unfolding with Generative Adversarial Networks
• Reconstructing Sparticle Mass Spectra using Hadronic Decays
• Identification of boosted, hadronically decaying W bosons and comparisons with ATLAS data taken at $\sqrt{s}=8$ TeV
• A neural network clustering algorithm for the ATLAS silicon pixel detector
• Novel Jet Observables from Machine Learning
• Machine Learning Uncertainties with Adversarial Neural Networks
• W-jet Tagging: Optimizing the Identification of Boosted Hadronically-Decaying W Bosons
• Search for a Higgs boson in the decay channel H to ZZ(*) to q qbar l-l+ in pp collisions at sqrt(s) = 7 TeV
• Lorentz Group Equivariant Neural Network for Particle Physics
• Finding physics signals with event deconstruction
• Qjets: A Non-Deterministic Approach to Tree-Based Jet Substructure
• Search for Single Top Quark Production at DZero Using Neural Networks
• (Machine) Learning to Do More with Less
• Quark-Gluon Tagging: Machine Learning vs Detector
• Quark-Gluon tagging with Shower Deconstruction: Unearthing dark matter and Higgs couplings
• Deep-Learning Jets with Uncertainties and More
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• A Theory of Quark vs. Gluon Discrimination
• Per-Object Systematics using Deep-Learned Calibration
• Automating the Construction of Jet Observables with Machine Learning
• Infrared Safety of a Neural-Net Top Tagging Algorithm
• Towards Machine Learning Analytics for Jet Substructure
• Reports of My Demise Are Greatly Exaggerated: $N$-subjettiness Taggers Take On Jet Images
• Opening the black box of neural nets: case studies in stop/top discrimination
• Measurement of the cross-section of high transverse momentum vector bosons reconstructed as single jets and studies of jet substructure in $pp$ collisions at $\sqrt{s}$ = 7 TeV with the ATLAS detector
• An Optimal Observable for Color Singlet Identification
• Cutting Multiparticle Correlators Down to Size
• Machine learning techniques in searches for $t\bar{t}h$ in the $h\to b\bar{b}$ decay channel
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• A Search for the Higgs Boson Using Neural Networks in Events with Missing Energy and \boldit{b}-quark Jets in $p\bar{p}$ Collisions at $\sqrt{s}=1.96$ TeV
• Classification of Energy Flow Observables in Narrow Jets
• Jet tagging made easy

Cited by in corpus (28)

• Equivariant Energy Flow Networks for Jet Tagging
• How to Understand Limitations of Generative Networks
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Deep learning jet modifications in heavy-ion collisions
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Triggering on Emerging Jets
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• Learning to Identify Electrons
• Resolving Extreme Jet Substructure
• Learning to Identify Semi-Visible Jets
• Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States
• Is infrared-collinear safe information all you need for jet classification?
• Learning to Isolate Muons
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Interpretable deep learning models for the inference and classification of LHC data
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Riemannian Data preprocessing in Machine Learning to focus on QCD color structure
• Top-philic Machine Learning
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• NCoder -- A Quantum Field Theory approach to encoding data
• Deep-Learned Event Variables for Collider Phenomenology
• Designing Observables for Quantum Interference in Jets at Subleading Color
• Applying Machine Learning Techniques To Intermediate-Length Cascade Decays
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure
• Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
• Learnable cut flow for high energy physics
• Power Counting Energy Flow Polynomials