An implementation of neural simulation-based inference for parameter estimation in ATLAS

Abstract

Neural simulation-based inference is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary histograms. Such methods are promising for a range of measurements, including at the Large Hadron Collider, where no single observable may be optimal to scan over the entire theoretical phase space under consideration, or where binning data into histograms could result in a loss of sensitivity. This work develops a neural simulation-based inference framework for statistical inference, using neural networks to estimate probability density ratios, which enables the application to a full-scale analysis. It incorporates a large number of systematic uncertainties, quantifies the uncertainty due to the finite number of events in training samples, develops a method to construct confidence intervals, and demonstrates a series of intermediate diagnostic checks that can be performed to validate the robustness of the method. As an example, the power and feasibility of the method are assessed on simulated data for a simplified version of an off-shell Higgs boson couplings measurement in the four-lepton final states. This approach represents an extension to the standard statistical methodology used by the experiments at the Large Hadron Collider, and can benefit many physics analyses.

arXiv comment50 pages in total, author list starting page 33, 8 figures, 1 table, published by Rep. Prog. Phys. All figures including auxiliary figures are available at https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/SOFT-2023-01

References in corpus (25)

• Asymptotic formulae for likelihood-based tests of new physics
• An update on vector boson pair production at hadron colliders
• On the spin and parity of a single-produced resonance at the LHC
• Real-time gravitational-wave science with neural posterior estimation
• Parameterized Machine Learning for High-Energy Physics
• Measurements of the Higgs boson width and anomalous HVV couplings from on-shell and off-shell production in the four-lepton final state
• A Guide to Constraining Effective Field Theories with Machine Learning
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Exploring QCD matter in extreme conditions with Machine Learning
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Measurement of the inclusive jet cross-sections in proton--proton collisions at $\sqrt{s}=$8 TeV with the ATLAS detector
• Evaluating generative models in high energy physics
• Uncertainty Aware Learning for High Energy Physics
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Search for nonresonant pair production of Higgs bosons in the $b\bar{b}b\bar{b}$ final state in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Determination of jet calibration and energy resolution in proton-proton collisions at $\sqrt{s}$ = 8 TeV using the ATLAS detector
• Evidence of off-shell Higgs boson production from $ZZ$ leptonic decay channels and constraints on its total width with the ATLAS detector
• A simultaneous unbinned differential cross section measurement of twenty-four $Z$+jets kinematic observables with the ATLAS detector
• Measurements of $WH$ and $ZH$ production with Higgs boson decays into bottom quarks and direct constraints on the charm Yukawa coupling in $13\mathrm{TeV}$ $pp$ collisions with the ATLAS detector
• Back to the Formula -- LHC Edition
• 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
• Neural Simulation-Based Inference of the Neutron Star Equation of State directly from Telescope Spectra
• On the determination of probability density functions by using Neural Networks
• Operational Experience and R&D results using the Google Cloud for High Energy Physics in the ATLAS experiment
• Total cost of ownership and evaluation of Google cloud resources for the ATLAS experiment at the LHC

Cited by in corpus (9)

• Logarithmically-accurate and positive-definite NLO shower matching
• Unbinned inclusive cross-section measurements with machine-learned systematic uncertainties
• Trustworthy scientific inference with generative models
• Observable Optimization for Precision Theory: Machine Learning Energy Correlators
• Data-Driven High-Dimensional Statistical Inference with Generative Models
• Exploring the BSM parameter space with Neural Network aided Simulation-Based Inference
• Searching for HWW Anomalous Couplings with Simulation-Based Inference
• Strong CWoLa: Binary Classification Without Background Simulation
• Polarized Target Nuclear Magnetic Resonance Measurements with Deep Neural Networks