Per-Object Systematics using Deep-Learned Calibration

Abstract

We show how to treat systematic uncertainties using Bayesian deep networks for regression. First, we analyze how these networks separately trace statistical and systematic uncertainties on the momenta of boosted top quarks forming fat jets. Next, we propose a novel calibration procedure by training on labels and their error bars. Again, the network cleanly separates the different uncertainties. As a technical side effect, we show how Bayesian networks can be extended to describe non-Gaussian features.

References in corpus (49)

• Adam: A Method for Stochastic Optimization
• An Introduction to PYTHIA 8.2
• Variational Inference: A Review for Statisticians
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• ParticleNet: Jet Tagging via Particle Clouds
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Classification without labels: Learning from mixed samples in high energy physics
• Stop Reconstruction with Tagged Tops
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Searching for New Physics with Deep Autoencoders
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Deep-learned Top Tagging with a Lorentz Layer
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• QCD or What?
• Quark and Gluon Jet Substructure
• What is the Machine Learning?
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Energy flow polynomials: A complete linear basis for jet substructure
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Variational Autoencoders for New Physics Mining at the Large Hadron Collider
• QCD-Aware Recursive Neural Networks for Jet Physics
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• Learning to Classify from Impure Samples with High-Dimensional Data
• Boosting $H\to b\bar{b}$ with Machine Learning
• How Much Information is in a Jet?
• Weakly Supervised Classification in High Energy Physics
• Recursive Neural Networks in Quark/Gluon Tagging
• Novel Jet Observables from Machine Learning
• Machine Learning Uncertainties with Adversarial Neural Networks
• (Machine) Learning to Do More with Less
• Quark-Gluon Tagging: Machine Learning vs Detector
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Deep-Learning Jets with Uncertainties and More
• Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
• Infrared Safety of a Neural-Net Top Tagging Algorithm
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• Reports of My Demise Are Greatly Exaggerated: $N$-subjettiness Taggers Take On Jet Images
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Opening the black box of neural nets: case studies in stop/top discrimination
• Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
• Investigating the Topology Dependence of Quark and Gluon Jets
• Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments
• CapsNets Continuing the Convolutional Quest

Cited by in corpus (26)

• Machine Learning and LHC Event Generation
• Understanding Event-Generation Networks via Uncertainties
• Event Generators for High-Energy Physics Experiments
• Generative Networks for Precision Enthusiasts
• Uncertainty Aware Learning for High Energy Physics
• Mapping Machine-Learned Physics into a Human-Readable Space
• Two Invertible Networks for the Matrix Element Method
• Measuring QCD Splittings with Invertible Networks
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• Returning CP-Observables to The Frames They Belong
• The Landscape of Unfolding with Machine Learning
• Precision-Machine Learning for the Matrix Element Method
• Optimizing Observables with Machine Learning for Better Unfolding
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• TensorBNN: Bayesian Inference for Neural Networks using Tensorflow
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• Advancing Tools for Simulation-Based Inference
• Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors
• Generative Unfolding with Distribution Mapping
• Unifying Simulation and Inference with Normalizing Flows
• Amplitude Uncertainties Everywhere All at Once
• Uncertainty Quantification From Scaling Laws in Deep Neural Networks
• Extrapolating Jet Radiation with Autoregressive Transformers
• Amplitude Surrogates for Multi-Jet Processes
• Classification of Fermi-LAT blazars with Bayesian neural networks