Enhancing searches for resonances with machine learning and moment decomposition

Abstract

A key challenge in searches for resonant new physics is that classifiers trained to enhance potential signals must not induce localized structures. Such structures could result in a false signal when the background is estimated from data using sideband methods. A variety of techniques have been developed to construct classifiers which are independent from the resonant feature (often a mass). Such strategies are sufficient to avoid localized structures, but are not necessary. We develop a new set of tools using a novel moment loss function (Moment Decomposition or MoDe) which relax the assumption of independence without creating structures in the background. By allowing classifiers to be more flexible, we enhance the sensitivity to new physics without compromising the fidelity of the background estimation.

arXiv comment22 pages, 9 figures; final published version, added affiliations, appended acknowledgments

References in corpus (30)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Measuring and testing dependence by correlation of distances
• Identifying Boosted Objects with N-subjettiness
• Deep Learning and its Application to LHC Physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Jet-Images -- Deep Learning Edition
• Strategies to Identify Boosted Tops
• Power Counting to Better Jet Observables
• What is the Machine Learning?
• Machine and Deep Learning Applications in Particle Physics
• Top Jets at the LHC
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• DisCo Fever: Robust Networks Through Distance Correlation
• Machine Learning Uncertainties with Adversarial Neural Networks
• ABCDisCo: Automating the ABCD Method with Machine Learning
• A deep neural network to search for new long-lived particles decaying to jets
• uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
• New approach to identifying boosted hadronically-decaying particle using jet substructure in its center-of-mass frame
• Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
• Mass Agnostic Jet Taggers
• QBDT, a new boosting decision tree method with systematic uncertainties into training for High Energy Physics
• Reducing the dependence of the neural network function to systematic uncertainties in the input space
• A search for baryon- and lepton-number violating decays of $\Lambda$ hyperons using the CLAS detector at Jefferson Laboratory
• New approaches for boosting to uniformity

Cited by in corpus (11)

• Uncertainty Aware Learning for High Energy Physics
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• On the BSM reach of four top production at the LHC
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Meta-learning and data augmentation for mass-generalised jet taggers
• Domain-Adversarial Graph Neural Networks for $\Lambda$ Hyperon Identification with CLAS12
• Decorrelation using Optimal Transport
• Designing Observables for Measurements with Deep Learning
• Enhancing generalization in high energy physics using white-box adversarial attacks