Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
arXiv:2205.03413 · doi:10.1103/PhysRevLett.129.082001
Abstract
Calibration is a common experimental physics problem, whose goal is to infer the value and uncertainty of an unobservable quantity Z given a measured quantity X. Additionally, one would like to quantify the extent to which X and Z are correlated. In this paper, we present a machine learning framework for performing frequentist maximum likelihood inference with Gaussian uncertainty estimation, which also quantifies the mutual information between the unobservable and measured quantities. This framework uses the Donsker-Varadhan representation of the Kullback-Leibler divergence -- parametrized with a novel Gaussian Ansatz -- to enable a simultaneous extraction of the maximum likelihood values, uncertainties, and mutual information in a single training. We demonstrate our framework by extracting jet energy corrections and resolution factors from a simulation of the CMS detector at the Large Hadron Collider. By leveraging the high-dimensional feature space inside jets, we improve upon the nominal CMS jet resolution by upwards of 15%.
arXiv comment7 pages, 1 figure, 1 table, code available at https://github.com/rikab/GaussianAnsatz; v3: minor updates to match journal version; v4: reference updates
References in corpus (42)
- PYTHIA 6.4 Physics and Manual
- PYTHIA 6.2 Physics and Manual
- The anti-k_t jet clustering algorithm
- FastJet user manual
- Dispelling the N^3 myth for the Kt jet-finder
- Determination of Jet Energy Calibration and Transverse Momentum Resolution in CMS
- Estimating divergence functionals and the likelihood ratio by convex risk minimization
- Jet energy scale and resolution in the CMS experiment in pp collisions at 8 TeV
- Jet energy scale measurements and their systematic uncertainties in proton-proton collisions at TeV with the ATLAS detector
- Jet energy measurement and its systematic uncertainty in proton-proton collisions at TeV with the ATLAS detector
- Electron and photon reconstruction and identification with the CMS experiment at the CERN LHC
- Performance of missing transverse momentum reconstruction in proton-proton collisions at 13 TeV using the CMS detector
- Energy Flow Networks: Deep Sets for Particle Jets
- Search for squarks and gluinos with the ATLAS detector in final states with jets and missing transverse momentum using 4.7 fb^-1 of sqrt(s) = 7 TeV proton-proton collision data
- Learning New Physics from a Machine
- Search for new phenomena in events with an energetic jet and missing transverse momentum in collisions at TeV with the ATLAS detector
- Pileup Mitigation with Machine Learning (PUMML)
- Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
- MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
- Exploring the Space of Jets with CMS Open Data
- A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
- Deep-Learning Jets with Uncertainties and More
- Per-Object Systematics using Deep-Learned Calibration
- E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
- Deep Neural Networks for Energy and Position Reconstruction in EXO-200
- Determination of jet calibration and energy resolution in proton-proton collisions at = 8 TeV using the ATLAS detector
- Cosmic Ray Spectrum from 250 TeV to 10 PeV using IceTop
- A deep neural network for simultaneous estimation of b jet energy and resolution
- Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
- Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
- Machine Learning based jet momentum reconstruction in heavy-ion collisions
- On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters
- Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
- Pile-Up Mitigation using Attention
- Bayesian Neural Networks for Fast SUSY Predictions
- Significance Variables
- Parametrizing the Detector Response with Neural Networks
- Bias and Priors in Machine Learning Calibrations for High Energy Physics
- Mathematical Properties of Numerical Inversion for Jet Calibrations
- Calorimetric Measurement of Multi-TeV Muons via Deep Regression
- Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers
- Energy reconstruction in a liquid argon calorimeter cell using convolutional neural networks