Uncertainty Aware Learning for High Energy Physics

Abstract

Machine learning techniques are becoming an integral component of data analysis in High Energy Physics (HEP). These tools provide a significant improvement in sensitivity over traditional analyses by exploiting subtle patterns in high-dimensional feature spaces. These subtle patterns may not be well-modeled by the simulations used for training machine learning methods, resulting in an enhanced sensitivity to systematic uncertainties. Contrary to the traditional wisdom of constructing an analysis strategy that is invariant to systematic uncertainties, we study the use of a classifier that is fully aware of uncertainties and their corresponding nuisance parameters. We show that this dependence can actually enhance the sensitivity to parameters of interest. Studies are performed using a synthetic Gaussian dataset as well as a more realistic HEP dataset based on Higgs boson decays to tau leptons. For both cases, we show that the uncertainty aware approach can achieve a better sensitivity than alternative machine learning strategies.

18 pages, 14 figures

References in corpus (48)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• A Brief Introduction to PYTHIA 8.1
• A general framework for implementing NLO calculations in shower Monte Carlo programs: the POWHEG BOX
• A New Method for Combining NLO QCD with Shower Monte Carlo Algorithms
• Matching NLO QCD computations with Parton Shower simulations: the POWHEG method
• Unsupervised Domain Adaptation by Backpropagation
• Machine learning and the physical sciences
• Event generation with SHERPA 1.1
• ALPGEN, a generator for hard multiparton processes in hadronic collisions
• Combined Measurement of the Higgs Boson Mass in $pp$ Collisions at $\sqrt{s}=7$ and 8 TeV with the ATLAS and CMS Experiments
• Herwig 7.0 / Herwig++ 3.0 Release Note
• Deep Learning and its Application to LHC Physics
• L2 Regularization for Learning Kernels
• The Hubble Constant
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Higgs production via gluon fusion in the POWHEG approach in the SM and in the MSSM
• Evidence for the Higgs-boson Yukawa coupling to tau leptons with the ATLAS detector
• Parameterized Machine Learning for High-Energy Physics
• A New Mass Reconstruction Technique for Resonances Decaying to di-tau
• Mining gold from implicit models to improve likelihood-free inference
• Constraining Effective Field Theories with Machine Learning
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• A Guide to Constraining Effective Field Theories with Machine Learning
• Machine and Deep Learning Applications in Particle Physics
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• Nuisance hardened data compression for fast likelihood-free inference
• Automatic physical inference with information maximising neural networks
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Understanding Event-Generation Networks via Uncertainties
• DisCo Fever: Robust Networks Through Distance Correlation
• Machine Learning Uncertainties with Adversarial Neural Networks
• Modern Machine Learning and Particle Physics
• 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
• A deep neural network to search for new long-lived particles decaying to jets
• Deep-Learning Jets with Uncertainties and More
• INFERNO: Inference-Aware Neural Optimisation
• uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
• Per-Object Systematics using Deep-Learned Calibration
• 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
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• 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
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review

Cited by in corpus (19)

• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• One-loop matrix element emulation with factorisation awareness
• Learning to Identify Semi-Visible Jets
• An implementation of neural simulation-based inference for parameter estimation in ATLAS
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Bayesian Probabilistic Modelling for Four-Tops at the LHC
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• Interpretable deep learning models for the inference and classification of LHC data
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Improving Robustness of Jet Tagging Algorithms with Adversarial Training
• Exploring the Universality of Hadronic Jet Classification
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Designing Observables for Measurements with Deep Learning
• Observable Optimization for Precision Theory: Machine Learning Energy Correlators