Machine Learning Uncertainties with Adversarial Neural Networks

Abstract

Machine Learning is a powerful tool to reveal and exploit correlations in a multi-dimensional parameter space. Making predictions from such correlations is a highly non-trivial task, in particular when the details of the underlying dynamics of a theoretical model are not fully understood. Using adversarial networks, we include a priori known sources of systematic and theoretical uncertainties during the training. This paves the way to a more reliable event classification on an event-by-event basis, as well as novel approaches to perform parameter fits of particle physics data. We demonstrate the benefits of the method explicitly in an example considering effective field theory extensions of Higgs boson production in association with jets.

10 pages, 6 figures, v2: published version

References in corpus (22)

• VBFNLO: A parton level Monte Carlo for processes with electroweak bosons
• Classification without labels: Learning from mixed samples in high energy physics
• Anomaly Detection for Resonant New Physics with Machine Learning
• Observation of $\mathrm{t}\overline{\mathrm{t}}$H production
• Complete Higgs Sector Constraints on Dimension-6 Operators
• Next-to-Leading order Higgs + 2 jet production via gluon fusion
• Constraining Effective Field Theories with Machine Learning
• Mass Effects in the Higgs-Gluon Coupling: Boosted vs Off-Shell Production
• What is the Machine Learning?
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Search for a standard model Higgs boson produced in association with a top-quark pair and decaying to bottom quarks using a matrix element method
• Effective Theories and Measurements at Colliders
• Novel Jet Observables from Machine Learning
• Boosted Higgs Shapes
• Monte Carlo studies of the jet activity in Higgs + 2 jet events
• Resolving the Higgs-Gluon Coupling with Jets
• LHC multijet events as a probe for anomalous dimension-six gluon interactions
• Opening the black box of neural nets: case studies in stop/top discrimination
• Higgs characterisation in the presence of theoretical uncertainties and invisible decays
• Quark jet versus gluon jet: fully-connected neural networks with high-level features
• Jet-associated resonance spectroscopy

Cited by in corpus (39)

• Anomaly Detection with Density Estimation
• QCD or What?
• Simulation Assisted Likelihood-free Anomaly Detection
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• 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
• Towards the ultimate differential SMEFT analysis
• Uncertainty Aware Learning for High Energy Physics
• Mapping Machine-Learned Physics into a Human-Readable Space
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Per-Object Systematics using Deep-Learned Calibration
• Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
• Exploring anomalous couplings in Higgs boson pair production through shape analysis
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Approaching robust EFT limits for CP-violation in the Higgs sector
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Enhancing searches for resonances with machine learning and moment decomposition
• On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
• Electroweak Top Couplings, Partial Compositeness and Top Partner Searches
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Meta-learning and data augmentation for mass-generalised jet taggers
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Deeply Learned Preselection of Higgs Dijet Decays at Future Lepton Colliders
• Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors
• Observation of the Singly Cabibbo-Suppressed Decay ${\Lambda }_c^{+}\to p{\pi }^0$
• Exploring the Universality of Hadronic Jet Classification
• Designing Observables for Measurements with Deep Learning
• Search for the radiative leptonic decay $D^{+}\to \gamma e^{+}{\nu }_e$ using Deep Learning