Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
arXiv:2404.14332 · doi:10.21468/SciPostPhys.18.4.117
Abstract
The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider.
Submission to SciPost
References in corpus (41)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The anti-k_t jet clustering algorithm
- An Introduction to PYTHIA 8.2
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- Score-Based Generative Modeling through Stochastic Differential Equations
- Measurement of the differential cross section for top quark pair production in pp collisions at sqrt(s) = 8 TeV
- Measurement of differential top-quark pair production cross sections in pp collisions at sqrt(s) = 7 TeV
- OmniFold: A Method to Simultaneously Unfold All Observables
- Measurements of top-quark pair differential cross-sections in the lepton+jets channel in collisions at TeV using the ATLAS detector
- TUnfold: an algorithm for correcting migration effects in high energy physics
- Measurement of differential cross sections for top quark pair production using the lepton+jets final state in proton-proton collisions at 13 TeV
- Measurement of the top quark mass in the lepton+jets channel from TeV ATLAS data and combination with previous results
- Score-based Generative Models for Calorimeter Shower Simulation
- Measurements of normalized differential cross-sections for ttbar production in pp collisions at sqrt(s) = 7 TeV using the ATLAS detector
- Measurements of top quark pair relative differential cross-sections with ATLAS in pp collisions at sqrt(s) = 7 TeV
- Invertible Networks or Partons to Detector and Back Again
- Measurements of top-quark pair differential and double-differential cross-sections in the +jets channel with collisions at TeV using the ATLAS detector
- How to GAN away Detector Effects
- GANplifying Event Samples
- Generative Networks for Precision Enthusiasts
- A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
- Interpreting top-quark LHC measurements in the standard-model effective field theory
- Fast Point Cloud Generation with Diffusion Models in High Energy Physics
- CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
- Measurements of top-quark pair differential cross-sections in the lepton+jets channel in collisions at =13 TeV using the ATLAS detector
- Uncertainty Aware Learning for High Energy Physics
- PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
- Learning to Simulate High Energy Particle Collisions from Unlabeled Data
- Measurement of the integrated and differential t-tbar production cross sections for high-pt top quarks in pp collisions at sqrt(s) = 8 TeV
- CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
- Measurements of differential cross sections of top quark pair production in association with jets in collisions at TeV using the ATLAS detector
- PC-Droid: Faster diffusion and improved quality for particle cloud generation
- Disentangling Quarks and Gluons with CMS Open Data
- Improving Generative Model-based Unfolding with Schrödinger Bridges
- Multidifferential study of identified charged hadron distributions in -tagged jets in proton-proton collisions at 13 TeV
- High-dimensional and Permutation Invariant Anomaly Detection
- Unbinned Deep Learning Jet Substructure Measurement in High ep collisions at HERA
- Precision-Machine Learning for the Matrix Element Method
- Refining Fast Calorimeter Simulations with a Schrödinger Bridge
- EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion
- CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
Cited by in corpus (7)
- CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation
- Generative Unfolding with Distribution Mapping
- Machine Learning-Assisted Unfolding for Neutrino Cross-section Measurements with the OmniFold Technique
- Tools for Unbinned Unfolding
- How to Unfold Top Decays
- Learnable cut flow for high energy physics
- ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics