Full event particle-level unfolding with variable-length latent variational diffusion

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 pro...

Full description

Saved in:
Bibliographic Details
Main Author: Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
Format: Article
Language:English
Published: SciPost 2025-04-01
Series:SciPost Physics
Online Access:https://scipost.org/SciPostPhys.18.4.117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737572049223680
author Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
author_facet Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
author_sort Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
collection DOAJ
description 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 $t\bar{t}$ production at the Large Hadron Collider.
format Article
id doaj-art-3a7f55c9959d47ba81f62ca80a691445
institution DOAJ
issn 2542-4653
language English
publishDate 2025-04-01
publisher SciPost
record_format Article
series SciPost Physics
spelling doaj-art-3a7f55c9959d47ba81f62ca80a6914452025-08-20T03:06:52ZengSciPostSciPost Physics2542-46532025-04-0118411710.21468/SciPostPhys.18.4.117Full event particle-level unfolding with variable-length latent variational diffusionAlexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel WhitesonThe 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 $t\bar{t}$ production at the Large Hadron Collider.https://scipost.org/SciPostPhys.18.4.117
spellingShingle Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
Full event particle-level unfolding with variable-length latent variational diffusion
SciPost Physics
title Full event particle-level unfolding with variable-length latent variational diffusion
title_full Full event particle-level unfolding with variable-length latent variational diffusion
title_fullStr Full event particle-level unfolding with variable-length latent variational diffusion
title_full_unstemmed Full event particle-level unfolding with variable-length latent variational diffusion
title_short Full event particle-level unfolding with variable-length latent variational diffusion
title_sort full event particle level unfolding with variable length latent variational diffusion
url https://scipost.org/SciPostPhys.18.4.117
work_keys_str_mv AT alexandershmakovkevingreifmichaeljamesfentonaishikghoshpierrebaldidanielwhiteson fulleventparticlelevelunfoldingwithvariablelengthlatentvariationaldiffusion