Hunting for bumps in the margins

Abstract

Data driven modelling is vital to many analyses at collider experiments, however the derived inference of physical properties becomes subject to details of the model fitting procedure. This work brings a principled Bayesian picture, based on the marginal likelihood, of both data modelling and signal extraction to a common collider physics scenario. First the marginal likelihood based method is used to propose a more principled construction of the background process, systematically exploring a variety of candidate shapes. Second the picture is extended to propose the marginal likelihood as a useful tool for anomaly detection challenges in particle physics. This proposal offers insight into both precise background model determination and demonstrates a flexible method to extend signal determination beyond a simple bump hunt.

arXiv comment10 pages, 6 figures, accepted to JINST

References in corpus (20)

• Herwig++ Physics and Manual
• Bayes in the sky: Bayesian inference and model selection in cosmology
• Herwig 7.0 / Herwig++ 3.0 Release Note
• PolyChord: next-generation nested sampling
• Curvature tension: evidence for a closed universe
• Robust Independent Validation of Experiment and Theory: Rivet version 3
• Search for new resonances in mass distributions of jet pairs using 139 fb${}^{-1}$ of $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Search for high mass dijet resonances with a new background prediction method in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Handling uncertainties in background shapes: the discrete profiling method
• anesthetic: nested sampling visualisation
• Measurements of Higgs boson production cross sections and couplings in the diphoton decay channel at $\sqrt{s}=$ 13 TeV
• On hypothesis testing, trials factor, hypertests and the BumpHunter
• fgivenx: A Python package for functional posterior plotting
• maxsmooth: Rapid Maximally Smooth Function Fitting With Applications in Global 21-cm Cosmology
• Bayesian evidence for the tensor-to-scalar ratio $r$ and neutrino masses $m_{\nu }$: Effects of uniform vs logarithmic priors
• Label Switching Problem in Bayesian Analysis for Gravitational Wave Astronomy
• Bayesian sparse reconstruction: a brute-force approach to astronomical imaging and machine learning
• Exploring phase space with Nested Sampling
• Bayesian and frequentist approaches to resonance searches
• Bayesian inference to study a signal with two or more decaying particles in a non-resonant background

Cited by in corpus (3)

• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Inferring correlated distributions: boosted top jets
• Log Gaussian Cox Process Background Modeling in High Energy Physics