Fast BIB simulation at a future Muon Collider with generative machine learning
Abstract
Beam-induced background (BIB) from muon decay products will be an overwhelming and unavoidable background at a future Muon Collider. In order to develop robust event reconstruction algorithms, we need large amounts of accurate BIB simulation to test on. BIB simulation is currently compute-limited: the simulated sample presently used for BIB overlay, which statistically represents approximately 10% of a single unique event's worth of simulated BIB, requires on the order of 106 HS23·hours to generate and occupies approximately $100$ GB on disk. In this work, we develop the first machine learning models for fast BIB generation in tracking detectors. We consider two classes of architectures: a slower but higher-fidelity tabular diffusion model, and a faster but lower fidelity circular spline flow model. We find that both classes of architectures produce BIB hits and tracks that closely resemble those of available full simulation hits and tracks, and that the machine learning models can produce BIB in over an order of magnitude less time than what is needed to produce full simulation BIB. We release the model weights with the paper so that the Muon Collider community can use these fast BIB hits for future R&D.
Related
- Machine-learning discovery potential for a heavy Higgs boson in e+e-→ ZH at a future lepton collider
- Parnassus for the CLD Detector: A Generative Machine-Learning Surrogate for Detector Simulation and Reconstruction at the FCC-ee
- Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider
- Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
- Generative marginal learning for finite-size molecular simulation with application to stress calculation
BibTeX
@misc{mastandrea2026fast,
title = {{Fast BIB simulation at a future Muon Collider with generative machine learning}},
author = {Radha Mastandrea and Shiyu Peng and Benjamin Rosser and Matt LeBlanc},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.12054},
eprint = {2609.12054},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.12054},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Fast BIB simulation at a future Muon Collider with generative machine learning
AU - Radha Mastandrea
AU - Shiyu Peng
AU - Benjamin Rosser
AU - Matt LeBlanc
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.12054
UR - https://arxiv.org/abs/2609.12054
AB - Beam-induced background (BIB) from muon decay products will be an overwhelming and unavoidable background at a future Muon Collider. In order to develop robust event reconstruction algorithms, we need large amounts of accurate BIB simulation to test on. BIB simulation is currently compute-limited: the simulated sample presently used for BIB overlay, which statistically represents approximately 10% of a single unique event's worth of simulated BIB, requires on the order of 10^6 HS23·hours to generate and occupies approximately $100$ GB on disk. In this work, we develop the first machine learning models for fast BIB generation in tracking detectors. We consider two classes of architectures: a slower but higher-fidelity tabular diffusion model, and a faster but lower fidelity circular spline flow model. We find that both classes of architectures produce BIB hits and tracks that closely resemble those of available full simulation hits and tracks, and that the machine learning models can produce BIB in over an order of magnitude less time than what is needed to produce full simulation BIB. We release the model weights with the paper so that the Muon Collider community can use these fast BIB hits for future R&D.
ER -