Non-Parametric Data-Driven Background Modelling using Conditional Probabilities

Abstract

Background modelling is one of the main challenges in particle physics data analysis. Commonly employed strategies include the use of simulated events of the background processes, and the fitting of parametric background models to the observed data. However, reliable simulations are not always available or may be extremely costly to produce. As a result, in many cases, uncertainties associated with the accuracy or sample size of the simulation are the limiting factor in the analysis sensitivity. At the same time, parametric models are limited by the a priori unknown functional form and parameter values of the background distribution. These issues become ever more pressing when large datasets become available, as it is already the case at the CERN Large Hadron Collider, and when studying exclusive signatures involving hadronic backgrounds. Two novel and widely applicable non-parametric data-driven background modelling techniques are presented, which address these issues for a broad class of searches and measurements. The first, relying on ancestral sampling, uses data from a relaxed event selection to estimate a graph of conditional probability density functions of the variables used in the analysis, accounting for significant correlations. A background model is then generated by sampling events from this graph, before the full event selection is applied. In the second, a generative adversarial network is trained to estimate the joint probability density function of the variables used in the analysis. The training is performed on a relaxed event selection which excludes the signal region, and the network is conditioned on a blinding variable. Subsequently, the conditional probability density function is interpolated into the signal region to model the background. The application of each method on a benchmark analysis is presented in detail, and the performance is discussed.

arXiv comment33 pages, 18 figures

References in corpus (41)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Conditional Generative Adversarial Nets
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Parton distributions for the LHC Run II
• Event generation with SHERPA 1.1
• Generative Adversarial Network in Medical Imaging: A Review
• New parton distribution functions from a global analysis of quantum chromodynamics
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Deep Learning and its Application to LHC Physics
• Exotic Decays of the 125 GeV Higgs Boson
• Anomaly Detection with Density Estimation
• Substructure of high-p_T Jets at the LHC
• New Angles on Energy Correlation Functions
• How to GAN LHC Events
• A measurement of the Higgs boson mass in the diphoton decay channel
• Evidence for Higgs boson decay to a pair of muons
• Simulation Assisted Likelihood-free Anomaly Detection
• A search for the dimuon decay of the Standard Model Higgs boson with the ATLAS detector
• Machine and Deep Learning Applications in Particle Physics
• Top Jets at the LHC
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Handling uncertainties in background shapes: the discrete profiling method
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• A Living Review of Machine Learning for Particle Physics
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• Interpolation between multi-dimensional histograms using a new non-linear moment morphing method
• Modern Machine Learning and Particle Physics
• GANplifying Event Samples
• Search for Higgs and $Z$ Boson Decays to $J/\psi \gamma$ and ${\rm Y}(nS)\gamma$ with the ATLAS Detector
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• Searches for exclusive Higgs and $Z$ boson decays into $J/\psi \gamma$, $\psi (2S)\gamma$, and ${\rm Y}(nS)\gamma$ at $\sqrt{s}=13$ TeV with the ATLAS detector
• Search for exclusive Higgs and $Z$ boson decays to $\varphi \gamma$ and $\rho \gamma$ with the ATLAS detector
• Search for Higgs boson decays into a $Z$ boson and a light hadronically decaying resonance using 13 TeV $pp$ collision data from the ATLAS detector
• Search for Higgs and $Z$ Boson Decays to $\varphi \gamma$ with the ATLAS Detector
• Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description
• A survey of machine learning-based physics event generation

Cited by in corpus (5)

• Searches for exclusive Higgs and $Z$ boson decays into a vector quarkonium state and a photon using $139$ fb${}^{-1}$ of ATLAS $\sqrt{s}=13$ TeV proton$-$proton collision data
• Search for the rare decays $W^{+}\to D_s^{+}\gamma$ and $Z\to D^0\gamma$ at LHCb
• Search for the exclusive $W$ boson hadronic decays $W^{\pm }\to {\pi }^{\pm }\gamma$, $W^{\pm }\to K^{\pm }\gamma$ and $W^{\pm }\to {\rho }^{\pm }\gamma$ with the ATLAS detector
• Searches for exclusive Higgs boson decays into $D^{\ast }\gamma$ and $Z$ boson decays into $D^0\gamma$ and $K_s^0\gamma$ in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Data driven background estimation in HEP using Generative Adversarial Networks