发表机构
AGH University of Krakow; The Henryk Niewodniczański Institute of Nuclear Physics, Polish Academy of Sciences（克拉科夫AGH大学; 波兰科学院亨利克·涅沃德尼昌斯基核物理研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LHC上ALICE零度数量计模拟成本高的问题，提出结合归一化流、条件微调及物理驱动评估的框架，引入精细指标，其模型集成体在Wasserstein距离上优于基线。
AI 中文摘要
在LHC上模拟ALICE零度数量计（ZDC）中子探测器的响应计算成本高昂，需要复杂的蒙特卡罗链。我们开发了一种生成式代理模型，聚焦于归一化流（Normalizing Flows，NFs）。通过迁移学习，我们在整个不平衡数据集上进行预训练，并采用两种渐进式解冻方案为不同粒子类型（γ、n、Λ、K_S^0、Σ^+）微调专用模型。由于Wasserstein距离等标准ZDC指标会忽略条件结构，我们引入了更精细的指标：条件加权平均绝对误差（MAE）、离散度比率和Jaccard共激活误差，这些指标能更好地捕捉与物理相关的输入-输出依赖关系和响应变异性。我们的微调模型集成体取得了1.61±0.02的Wasserstein距离，在所有指标上均优于基线模型。本研究提供了一种可推广的基于NF的LHC探测器模拟框架，结合了NFs、条件微调以及物理驱动的评估方法。
英文摘要
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 ($γ$, $n$, $Λ$, $K_S^0$, $Σ^+$) 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.
CommentsThis paper has been accepted for presentation at the 16th International Conference on Parallel Processing & Applied Mathematics (PPAM 2026)
