A Guide to Constraining Effective Field Theories with Machine Learning

Abstract

We develop, discuss, and compare several inference techniques to constrain theory parameters in collider experiments. By harnessing the latent-space structure of particle physics processes, we extract extra information from the simulator. This augmented data can be used to train neural networks that precisely estimate the likelihood ratio. The new methods scale well to many observables and high-dimensional parameter spaces, do not require any approximations of the parton shower and detector response, and can be evaluated in microseconds. Using weak-boson-fusion Higgs production as an example process, we compare the performance of several techniques. The best results are found for likelihood ratio estimators trained with extra information about the score, the gradient of the log likelihood function with respect to the theory parameters. The score also provides sufficient statistics that contain all the information needed for inference in the neighborhood of the Standard Model. These methods enable us to put significantly stronger bounds on effective dimension-six operators than the traditional approach based on histograms. They also outperform generic machine learning methods that do not make use of the particle physics structure, demonstrating their potential to substantially improve the new physics reach of the LHC legacy results.

arXiv commentSee also the companion publication "Constraining Effective Field Theories with Machine Learning" at arXiv:1805.00013, a brief introduction presenting the key ideas. The code for these studies is available at https://github.com/johannbrehmer/higgs_inference . v2: Added references. v3: Improved description of algorithms, added references. v4: Clarified text, added references

References in corpus (41)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• A Brief Introduction to PYTHIA 8.1
• WaveNet: A Generative Model for Raw Audio
• Asymptotic formulae for likelihood-based tests of new physics
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Dimension-Six Terms in the Standard Model Lagrangian
• Conditional Image Generation with PixelCNN Decoders
• Pixel Recurrent Neural Networks
• Kernel Estimation in High-Energy Physics
• Spin determination of single-produced resonances at hadron colliders
• Determining the Structure of Higgs Couplings at the LHC
• On the spin and parity of a single-produced resonance at the LHC
• Patterns of Deviation from the Standard Model
• A Precision Measurement of the Mass of the Top Quark
• Parameterized Machine Learning for High-Energy Physics
• Anomalous Higgs boson couplings in vector boson fusion at the CERN LHC
• Constraining Effective Field Theories with Machine Learning
• Constraining anomalous Higgs boson couplings to the heavy flavor fermions using matrix element techniques
• Finding top quarks with shower deconstruction
• Finding physics signals with shower deconstruction
• Jet angular correlation in vector-boson fusion processes at hadron colliders
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• Automatic physical inference with information maximising neural networks
• Pushing Higgs Effective Theory to its Limits
• Higgs Quantum Numbers in Weak Boson Fusion
• Better Higgs-CP Tests Through Information Geometry
• Finding physics signals with event deconstruction
• Better Higgs Measurements Through Information Geometry
• The Matrix Element Method and QCD Radiation
• Unravelling $t\bar{t}h$ via the matrix element method
• Precision studies of the Higgs boson decay channel H -> ZZ -> 4l with MEKD
• Mad-Maximized Higgs Pair Analyses
• Extending the Matrix Element Method beyond the Born approximation: Calculating event weights at next-to-leading order accuracy
• Polishing a shiny Higgs with matrix elements
• Maximum Significance at the LHC and Higgs Decays to Muons
• Measuring the Higgs-bottom coupling in weak boson fusion
• Finding the Higgs boson in decays to Z gamma using the matrix element method at Next-to-Leading Order
• The Matrix Element Method at next-to-leading order QCD for hadronic collisions: Single top-quark production at the LHC as an example application
• Accelerated Matrix Element Method with Parallel Computing
• MadMax, or Where Boosted Significances Come From

Cited by in corpus (91)

• Machine learning and the physical sciences
• The frontier of simulation-based inference
• Fast likelihood-free cosmology with neural density estimators and active learning
• Learning New Physics from a Machine
• OmniFold: A Method to Simultaneously Unfold All Observables
• Mining gold from implicit models to improve likelihood-free inference
• Constraining Effective Field Theories with Machine Learning
• Simulation Assisted Likelihood-free Anomaly Detection
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Guiding New Physics Searches with Unsupervised Learning
• Nuisance hardened data compression for fast likelihood-free inference
• Machine Learning and LHC Event Generation
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• How to GAN away Detector Effects
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Uncertainty Aware Learning for High Energy Physics
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• INFERNO: Inference-Aware Neural Optimisation
• Exploring SMEFT in VH with Machine Learning
• Presenting Unbinned Differential Cross Section Results
• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• Accurate Machine Learning Atmospheric Retrieval via a Neural Network Surrogate Model for Radiative Transfer
• Machine learning the Higgs boson-top quark CP phase
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Benchmarking simplified template cross sections in $WH$ production
• Boosted decision trees in the era of new physics: a smuon analysis case study
• Exploring anomalous couplings in Higgs boson pair production through shape analysis
• Constraining CP-violation in the Higgs-top-quark interaction using machine-learning-based inference
• Parametrized classifiers for optimal EFT sensitivity
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Higgs boson tagging with the Lund jet plane
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• Returning CP-Observables to The Frames They Belong
• A Reduced basis for CP violation in SMEFT at colliders and its application to Diboson production
• Using a nested anomaly detection machine learning algorithm to study the neutral triple gauge couplings at an \texorpdfstring{$e^{+}{e}^{-}$}{e+e-} collider
• Learning to pinpoint effective operators at the LHC: a study of the $t\bar{t}b\bar{b}$ signature
• Learning Likelihood Ratios with Neural Network Classifiers
• Unbinned multivariate observables for global SMEFT analyses from machine learning
• Effective LHC measurements with matrix elements and machine learning
• Polarization fraction measurement in ZZ scattering using deep learning
• Precision-Machine Learning for the Matrix Element Method
• Tree boosting for learning EFT parameters
• Energy Correlators of Hadronically Decaying Electroweak Bosons
• ELSA -- Enhanced latent spaces for improved collider simulations
• Using Machine Learning to disentangle LHC signatures of Dark Matter candidates
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Bayesian Neural Networks for Fast SUSY Predictions
• Likelihood-free inference with an improved cross-entropy estimator
• Exploration of Parameter Spaces Assisted by Machine Learning
• Back to the Formula -- LHC Edition
• Probing effective field theory operators in the associated production of top quarks with a Z boson in multilepton final states at $\sqrt{s}=$ 13 TeV
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Four-top quark physics at the LHC
• Measurement of off-shell Higgs boson production in the $H^{\ast }\to ZZ\to 4\ell$ decay channel using a neural simulation-based inference technique in 13 TeV $pp$ collisions with the ATLAS detector
• Debiasing Standard Siren Inference of the Hubble Constant with Marginal Neural Ratio Estimation
• Learning Multivariate New Physics
• Exoplanet atmosphere evolution: emulation with neural networks
• Reframing Jet Physics with New Computational Methods
• An implementation of neural simulation-based inference for parameter estimation in ATLAS
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Electroweak Top Couplings, Partial Compositeness and Top Partner Searches
• Resonance Searches with Machine Learned Likelihood Ratios
• Parameter Inference from Event Ensembles and the Top-Quark Mass
• Simulation-based inference in the search for CP violation in leptonic WH production
• XEFT, the challenging path up the hill: dim = 6 and dim = 8
• Advancing Tools for Simulation-Based Inference
• Neural Conditional Reweighting
• Distinguishing $W^{\prime }$ Signals at Hadron Colliders Using Neural Networks
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• Refinable modeling for unbinned SMEFT analyses
• Unbinned inclusive cross-section measurements with machine-learned systematic uncertainties
• Top-philic Machine Learning
• LHC EFT WG Note: SMEFT predictions, event reweighting, and simulation
• Constraints on standard model effective field theory for a Higgs boson produced in association with W or Z bosons in the H $\to \mathrm{b}\bar{\mathrm{b}}$ decay channel in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Designing Observables for Measurements with Deep Learning
• Equivariant neural networks for robust $\text{CP}$ observables
• Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
• BitHEP -- The Limits of Low-Precision ML in HEP
• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
• Searching for HWW Anomalous Couplings with Simulation-Based Inference
• Data-Driven High-Dimensional Statistical Inference with Generative Models
• Deep inference of simulated strong lenses in ground-based surveys
• Mixture Density Network Estimation of Continuous Variable Maximum Likelihood Using Discrete Training Samples
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• Probing effective operators in single top quark production in association with a lepton-neutrino pair