Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences

Abstract

We show that density models describing multiple observables with (i) hard boundaries and (ii) dependence on external parameters may be created using an auto-regressive Gaussian mixture model. The model is designed to capture how observable spectra are deformed by hypothesis variations, and is made more expressive by projecting data onto a configurable latent space. It may be used as a statistical model for scientific discovery in interpreting experimental observations, for example when constraining the parameters of a physical model or tuning simulation parameters according to calibration data. The model may also be sampled for use within a Monte Carlo simulation chain, or used to estimate likelihood ratios for event classification. The method is demonstrated on simulated high-energy particle physics data considering the anomalous electroweak production of a $Z$ boson in association with a dijet system at the Large Hadron Collider, and the accuracy of inference is tested using a realistic toy example. The developed methods are domain agnostic; they may be used within any field to perform simulation or inference where a dataset consisting of many real-valued observables has conditional dependence on external parameters.

arXiv comment42 pages, 20 figures, 6 tables. Simulated data, model files and code available at: https://dx.doi.org/10.48420/17136839

References in corpus (25)

• Auto-Encoding Variational Bayes
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• Generative Adversarial Networks
• An Introduction to Variational Autoencoders
• Dimension-Six Terms in the Standard Model Lagrangian
• The Standard Model as an Effective Field Theory
• General-purpose event generators for LHC physics
• Robust Independent Validation of Experiment and Theory: Rivet version 3
• Updated Global SMEFT Fit to Higgs, Diboson and Electroweak Data
• The SMEFTsim package, theory and tools
• Top, Higgs, Diboson and Electroweak Fit to the Standard Model Effective Field Theory
• Fast likelihood-free cosmology with neural density estimators and active learning
• How to GAN LHC Events
• Mining gold from implicit models to improve likelihood-free inference
• A Guide to Constraining Effective Field Theories with Machine Learning
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• Exploring SMEFT in VH with Machine Learning
• Differential cross-section measurements for the electroweak production of dijets in association with a $Z$ boson in proton-proton collisions at ATLAS
• Unsupervised Hadronic SUEP at the LHC
• Measurement of the cross-section for electroweak production of dijets in association with a $Z$ boson in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector

Cited by in corpus (1)

• Reconstruction of Missing Resonances Combining Nearest Neighbors Regressors and Neural Network Classifiers