An interpretable unsupervised representation learning for high precision measurement in particle physics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lv, Xing-Jian, Miao, De-Xing, Xu, Zi-Jun, Wang, Jian-Chun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914173265379328
author Lv, Xing-Jian
Miao, De-Xing
Xu, Zi-Jun
Wang, Jian-Chun
author_facet Lv, Xing-Jian
Miao, De-Xing
Xu, Zi-Jun
Wang, Jian-Chun
contents Unsupervised learning has been widely applied to various tasks in particle physics. However, existing models lack precise control over their learned representations, limiting physical interpretability and hindering their use for accurate measurements. We propose the Histogram AutoEncoder (HistoAE), an unsupervised representation learning network featuring a custom histogram-based loss that enforces a physically structured latent space. Applied to silicon microstrip detectors, HistoAE learns an interpretable two-dimensional latent space corresponding to the particle's charge and impact position. After simple post-processing, it achieves a charge resolution of $0.25\,e$ and a position resolution of $3\,μ\mathrm{m}$ on beam-test data, comparable to the conventional approach. These results demonstrate that unsupervised deep learning models can enable physically meaningful and quantitatively precise measurements. Moreover, the generative capacity of HistoAE enables straightforward extensions to fast detector simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22246
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An interpretable unsupervised representation learning for high precision measurement in particle physics
Lv, Xing-Jian
Miao, De-Xing
Xu, Zi-Jun
Wang, Jian-Chun
High Energy Physics - Experiment
Artificial Intelligence
Instrumentation and Detectors
Unsupervised learning has been widely applied to various tasks in particle physics. However, existing models lack precise control over their learned representations, limiting physical interpretability and hindering their use for accurate measurements. We propose the Histogram AutoEncoder (HistoAE), an unsupervised representation learning network featuring a custom histogram-based loss that enforces a physically structured latent space. Applied to silicon microstrip detectors, HistoAE learns an interpretable two-dimensional latent space corresponding to the particle's charge and impact position. After simple post-processing, it achieves a charge resolution of $0.25\,e$ and a position resolution of $3\,μ\mathrm{m}$ on beam-test data, comparable to the conventional approach. These results demonstrate that unsupervised deep learning models can enable physically meaningful and quantitatively precise measurements. Moreover, the generative capacity of HistoAE enables straightforward extensions to fast detector simulations.
title An interpretable unsupervised representation learning for high precision measurement in particle physics
topic High Energy Physics - Experiment
Artificial Intelligence
Instrumentation and Detectors
url https://arxiv.org/abs/2511.22246