Unifying Simulation and Inference with Normalizing Flows
arXiv:2404.18992 · doi:10.1103/PhysRevD.111.076004
Abstract
There have been many applications of deep neural networks to detector calibrations and a growing number of studies that propose deep generative models as automated fast detector simulators. We show that these two tasks can be unified by using maximum likelihood estimation (MLE) from conditional generative models for energy regression. Unlike direct regression techniques, the MLE approach is prior-independent and non-Gaussian resolutions can be determined from the shape of the likelihood near the maximum. Using an ATLAS-like calorimeter simulation, we demonstrate this concept in the context of calorimeter energy calibration.
13 pages, 7 figures; v3: matches published version
References in corpus (54)
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- Observation of a new boson with mass near 125 GeV in pp collisions at sqrt(s) = 7 and 8 TeV
- Observation of the diphoton decay of the Higgs boson and measurement of its properties
- CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
- Anomaly Detection with Density Estimation
- Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
- Event Generation with Normalizing Flows
- OmniFold: A Method to Simultaneously Unfold All Observables
- TUnfold: an algorithm for correcting migration effects in high energy physics
- Classifying Anomalies THrough Outer Density Estimation (CATHODE)
- i-flow: High-dimensional Integration and Sampling with Normalizing Flows
- Exploring phase space with Neural Importance Sampling
- Invertible Networks or Partons to Detector and Back Again
- CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
- How to GAN away Detector Effects
- Understanding Event-Generation Networks via Uncertainties
- Generative Networks for Precision Enthusiasts
- Targeting Multi-Loop Integrals with Neural Networks
- Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
- Resonant anomaly detection without background sculpting
- MadNIS -- Neural Multi-Channel Importance Sampling
- L2LFlows: Generating High-Fidelity 3D Calorimeter Images
- Learning to Simulate High Energy Particle Collisions from Unlabeled Data
- Per-Object Systematics using Deep-Learned Calibration
- Two Invertible Networks for the Matrix Element Method
- Measuring QCD Splittings with Invertible Networks
- Inference of cosmic-ray source properties by conditional invertible neural networks
- Measurement of the radius dependence of charged-particle jet suppression in Pb-Pb collisions at = 5.02 TeV
- A deep neural network for simultaneous estimation of b jet energy and resolution
- ν-Flows: Conditional Neutrino Regression
- Electromagnetic Showers Beyond Shower Shapes
- Learning the language of QCD jets with transformers
- Inductive Simulation of Calorimeter Showers with Normalizing Flows
- Machine Learning based jet momentum reconstruction in heavy-ion collisions
- Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
- The MadNIS Reloaded
- On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters
- Returning CP-Observables to The Frames They Belong
- Improving Generative Model-based Unfolding with Schrödinger Bridges
- CaloFlow for CaloChallenge Dataset 1
- High-dimensional and Permutation Invariant Anomaly Detection
- The Landscape of Unfolding with Machine Learning
- Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
- -Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
- Deeply Learning Deep Inelastic Scattering Kinematics
- Parametrizing the Detector Response with Neural Networks
- Calorimeter shower superresolution
- Towards a data-driven model of hadronization using normalizing flows
- New techniques for jet calibration with the ATLAS detector
- Calorimetric Measurement of Multi-TeV Muons via Deep Regression
- Mathematical Properties of Numerical Inversion for Jet Calibrations
- Optimising longitudinal and lateral calorimeter granularity for software compensation in hadronic showers using deep neural networks
- Anomaly detection with flow-based fast calorimeter simulators
- Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network