Metraipolis › archive › dc_f776fad1d2cf
Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation — arXiv:2608.12795
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12795
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:51.838Z
- SHA-256 of the archived text
4a480266c3ab33dd7f90b11bbc744e99b549f82e948cdf0a3f850a3c24d8f25e- Stable URL of this page
https://metraipolis.com/documento/dc_f776fad1d2cf
How to cite
Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation — arXiv:2608.12795 — arXiv (en), https://arxiv.org/abs/2608.12795 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f776fad1d2cf (Metraipolis archive dc_f776fad1d2cf, sha256 4a480266c3ab33dd7f90b11bbc744e99b549f82e948cdf0a3f850a3c24d8f25e)
BibTeX
@misc{dcf776fad1d2cf,
title = {Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation — arXiv:2608.12795},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12795},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f776fad1d2cf; sha256 4a480266c3ab33dd7f90b11bbc744e99b549f82e948cdf0a3f850a3c24d8f25e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12795. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Simulating the ALICE Zero Degree Calorimeter (ZDC) neutron detector responses at the LHC is computationally expensive, requiring complex Monte Carlo chains. We develop a generative surrogate, focusing on Normalizing Flows (NFs). Through transfer learning, we pre-train on the full imbalanced dataset and fine-tune specialized models for different particle types ($\gamma$, $n$, $\Lambda$, $K_S^0$, $\Sigma^+$) using two gradual-unfreezing schemes. As standard ZDC metrics like Wasserstein distance overlook conditional structure, we introduce refined metrics: conditional weighted MAE, dispersion ratio, and Jaccard co-activation error, that better capture physics-relevant input-output dependencies and response variability. Our ensemble of fine-tuned models achieves a Wasserstein distance of $1.61 \pm 0.02$, outperforming baselines across all metrics. This work provides a generalizable NF-based framework for LHC detector simulation, combining NFs, conditional fine-tuning, and physics-motivated evaluation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG). Categorie arXiv: Instrumentation and Detectors (physics.ins-det) ; Machine Learning (cs.LG); High Energy Physics - Experiment (hep-ex). Pagina del lavoro: https://arxiv.org/abs/2608.12795 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:20:35.898Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).