What is the Machine Learning?

Abstract

Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency. To address this concern, we explore a data planing procedure for identifying combinations of variables -- aided by physical intuition -- that can discriminate signal from background. Weights are introduced to smooth away the features in a given variable(s). New networks are then trained on this modified data. Observed decreases in sensitivity diagnose the variable's discriminating power. Planing also allows the investigation of the linear versus non-linear nature of the boundaries between signal and background. We demonstrate the efficacy of this approach using a toy example, followed by an application to an idealized heavy resonance scenario at the Large Hadron Collider. By unpacking the information being utilized by these algorithms, this method puts in context what it means for a machine to learn.

6 pages, 3 figures. Version published in PRD, discussion added

References in corpus (5)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• A generic anti-QCD jet tagger
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• New approaches for boosting to uniformity

Cited by in corpus (46)

• 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
• Searching for New Physics with Deep Autoencoders
• Learning New Physics from a Machine
• QCD or What?
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Energy flow polynomials: A complete linear basis for jet substructure
• Guiding New Physics Searches with Unsupervised Learning
• Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
• Gravitational wave signal recognition of O1 data by deep learning
• Novel Jet Observables from Machine Learning
• DisCo Fever: Robust Networks Through Distance Correlation
• Machine Learning Uncertainties with Adversarial Neural Networks
• Methodology study of machine learning for the neutron star equation of state
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Quark-Gluon Tagging: Machine Learning vs Detector
• An operational definition of quark and gluon jets
• Deep-Learning Jets with Uncertainties and More
• Supervised deep learning in high energy phenomenology: a mini review
• Mapping Machine-Learned Physics into a Human-Readable Space
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Equivariant Energy Flow Networks for Jet Tagging
• Per-Object Systematics using Deep-Learned Calibration
• Exploring anomalous couplings in Higgs boson pair production through shape analysis
• Mass Agnostic Jet Taggers
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Opening the black box of neural nets: case studies in stop/top discrimination
• Triggering on Emerging Jets
• Cataloging Accreted Stars within Gaia DR2 using Deep Learning
• Deep learning for the R-parity violating supersymmetry searches at the LHC
• Precision SMEFT bounds from the VBF Higgs at high transverse momentum
• CapsNets Continuing the Convolutional Quest
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• Learning Multivariate New Physics
• Enhancing searches for resonances with machine learning and moment decomposition
• Learning to Isolate Muons
• Interpretable deep learning models for the inference and classification of LHC data
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Meta-learning and data augmentation for mass-generalised jet taggers
• Boosted top tagging and its interpretation using Shapley values
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Decorrelation using Optimal Transport
• Deep-Learned Event Variables for Collider Phenomenology
• Energy Flow in Particle Collisions
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure
• Optimal event selection and categorization in high energy physics, Part 1: Signal discovery