Constraining Effective Field Theories with Machine Learning

Abstract

We present powerful new analysis techniques to constrain effective field theories at the LHC. By leveraging the structure of particle physics processes, we extract extra information from Monte-Carlo simulations, which can be used to train neural network models that estimate the likelihood ratio. These methods scale well to processes with many observables and theory parameters, do not require any approximations of the parton shower or detector response, and can be evaluated in microseconds. We show that they allow us to put significantly stronger bounds on dimension-six operators than existing methods, demonstrating their potential to improve the precision of the LHC legacy constraints.

arXiv commentSee also the companion publication "A Guide to Constraining Effective Field Theories with Machine Learning" at arXiv:1805.00020, an in-depth analysis of machine learning techniques for LHC measurements. The code for these studies is available at https://github.com/johannbrehmer/higgs_inference . v2: New schematic figure explaining the new algorithms, added references. v3, v4: Added references

References in corpus (25)

• 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
• Dimension-Six Terms in the Standard Model Lagrangian
• Spin determination of single-produced resonances at hadron colliders
• On the spin and parity of a single-produced resonance at the LHC
• A Precision Measurement of the Mass of the Top Quark
• Constraining anomalous Higgs boson couplings to the heavy flavor fermions using matrix element techniques
• A Guide to Constraining Effective Field Theories with Machine Learning
• Finding top quarks with shower deconstruction
• Finding physics signals with shower deconstruction
• 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 (96)

• Machine learning and the physical sciences
• The frontier of simulation-based inference
• Normalizing Flows for Probabilistic Modeling and Inference
• Energy Flow Networks: Deep Sets for Particle Jets
• 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
• Simulation Assisted Likelihood-free Anomaly Detection
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• A Guide to Constraining Effective Field Theories with Machine Learning
• Predictions of nuclear $\beta$-decay half-lives with machine learning and their impacts on $r$ process
• Machine and Deep Learning Applications in Particle Physics
• Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
• 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
• Reinterpretation of LHC Results for New Physics: Status and Recommendations after Run 2
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Machine Learning Uncertainties with Adversarial Neural Networks
• 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
• Towards the ultimate differential SMEFT analysis
• Uncertainty Aware Learning for High Energy Physics
• Nuclear liquid-gas phase transition with machine learning
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Publishing statistical models: Getting the most out of particle physics experiments
• INFERNO: Inference-Aware Neural Optimisation
• The Persistence of Large Scale Structures I: Primordial non-Gaussianity
• Exploring SMEFT in VH with Machine Learning
• Presenting Unbinned Differential Cross Section Results
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• Higgs Couplings without the Higgs
• Machine learning the Higgs boson-top quark CP phase
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• Prediction of Nuclear Charge Density Distribution with Feedback Neural Network
• Measuring QCD Splittings with Invertible Networks
• 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
• Black-box Bayesian inference for economic agent-based models
• Towards constraining warm dark matter with stellar streams through neural simulation-based inference
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• A Reduced basis for CP violation in SMEFT at colliders and its application to Diboson production
• Learning to pinpoint effective operators at the LHC: a study of the $t\bar{t}b\bar{b}$ signature
• Using a nested anomaly detection machine learning algorithm to study the neutral triple gauge couplings at an \texorpdfstring{$e^{+}{e}^{-}$}{e+e-} collider
• Combined SMEFT interpretation of Higgs, diboson, and top quark data from the LHC
• 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
• Tree boosting for learning EFT parameters
• ELSA -- Enhanced latent spaces for improved collider simulations
• Energy Correlators of Hadronically Decaying Electroweak Bosons
• Using Machine Learning to disentangle LHC signatures of Dark Matter candidates
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Likelihood-free inference with an improved cross-entropy estimator
• Exploration of Parameter Spaces Assisted by Machine Learning
• Back to the Formula -- LHC Edition
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Reframing Jet Physics with New Computational Methods
• Learning Multivariate New Physics
• Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States
• Search for $CP$ violation in ttH and tH production in multilepton channels in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Learning to Inflate
• Resonance Searches with Machine Learned Likelihood Ratios
• Electroweak Top Couplings, Partial Compositeness and Top Partner Searches
• Parameter Inference from Event Ensembles and the Top-Quark Mass
• 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
• OASIS: Optimal Analysis-Specific Importance Sampling for event generation
• Adding Pseudo-Observables to the Four-Lepton Experimentalist's Toolbox
• Refinable modeling for unbinned SMEFT analyses
• How machine learning conquers the unitary limit
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• A Neural Network Perturbation Theory Based on the Born Series
• Unbinned inclusive cross-section measurements with machine-learned systematic uncertainties
• 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
• LHC EFT WG Note: SMEFT predictions, event reweighting, and simulation
• BitHEP -- The Limits of Low-Precision ML in HEP
• Designing Observables for Measurements with Deep Learning
• Search for $CP$ violation in events with top quarks and Z bosons at $\sqrt{s}$ = 13 and 13.6 TeV
• Equivariant neural networks for robust $\text{CP}$ observables
• Data-Driven High-Dimensional Statistical Inference with Generative Models
• Searching for HWW Anomalous Couplings with Simulation-Based Inference
• Robustness of Neural Ratio and Posterior Estimators to Distributional Shifts for Population-Level Dark Matter Analysis in Strong Gravitational Lensing
• Deep inference of simulated strong lenses in ground-based surveys
• LSST Strong Lensing Systems Dark Matter Sensitivity Analysis with Neural Ratio Estimators