Reducing the dependence of the neural network function to systematic uncertainties in the input space

Abstract

Applications of neural networks to data analyses in natural sciences are complicated by the fact that many inputs are subject to systematic uncertainties. To control the dependence of the neural network function to variations of the input space within these systematic uncertainties, several methods have been proposed. In this work, we propose a new approach of training the neural network by introducing penalties on the variation of the neural network output directly in the loss function. This is achieved at the cost of only a small number of additional hyperparameters. It can also be pursued by treating all systematic variations in the form of statistical weights. The proposed method is demonstrated with a simple example, based on pseudo-experiments, and by a more complex example from high-energy particle physics.

References in corpus (14)

• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Performance of $b$-Jet Identification in the ATLAS Experiment
• Observation of Higgs boson production in association with a top quark pair at the LHC with the ATLAS detector
• Observation of Higgs boson decay to bottom quarks
• Observation of $H\to b\bar{b}$ decays and $VH$ production with the ATLAS detector
• Observation of $\mathrm{t}\overline{\mathrm{t}}$H production
• Performance of reconstruction and identification of $\tau$ leptons decaying to hadrons and ${\nu }_{\tau }$ in pp collisions at $\sqrt{s}=$ 13 TeV
• Cross-section measurements of the Higgs boson decaying into a pair of tau-leptons in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Automatic physical inference with information maximising neural networks
• Reconstruction of hadronic decay products of tau leptons with the ATLAS experiment
• INFERNO: Inference-Aware Neural Optimisation
• QBDT, a new boosting decision tree method with systematic uncertainties into training for High Energy Physics
• Identifying the relevant dependencies of the neural network response on characteristics of the input space

Cited by in corpus (17)

• Simulation Assisted Likelihood-free Anomaly Detection
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• DisCo Fever: Robust Networks Through Distance Correlation
• ABCDisCo: Automating the ABCD Method with Machine Learning
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• A Cautionary Tale of Decorrelating Theory Uncertainties
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Optimal statistical inference in the presence of systematic uncertainties using neural network optimization based on binned Poisson likelihoods with nuisance parameters
• Enhancing searches for resonances with machine learning and moment decomposition
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Deeply Learned Preselection of Higgs Dijet Decays at Future Lepton Colliders
• Advances in Multi-Variate Analysis Methods for New Physics Searches at the Large Hadron Collider
• Designing Observables for Measurements with Deep Learning
• Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC