AI 中文总结
研究高亮度 $e^+e^-$ 对撞机中束流诱导背景问题，提出 D$e^+e^-$ffusion 去噪扩散概率模型，经训练能再现 IPC 分布，通过模拟和分类器评估保真度，其生成事件速度比 Geant4 快近四个数量级，为 FCC-ee 设计研究提供快速模拟替代物。
AI 中文摘要
在高亮度 $e^+e^-$ 对撞机（如 FCC-ee）中，束流诱导背景主要由非相干对产生（IPC）主导，需要用专用蒙特卡罗（MC）事件发生器进行计算成本高昂的模拟。可靠的探测器和机器-探测器接口研究需要比现有 MC 实际可获得的事件样本大几个数量级的样本。为缓解这一瓶颈，我们提出 D$e^+e^-$ffusion，一种去噪扩散概率模型，作为快速 IPC 模拟的置换等变、集值替代物。在小的 GuineaPig++ 样本上训练后，D$e^+e^-$ffusion 能忠实地再现所有三个 IPC 产生过程的边缘和联合运动学、角度和位置分布。此外，我们通过将 Geant4 和 D$e^+e^-$ffusion 事件通过 CLD 顶点探测器的 Geant4 模拟传播，并训练基于变压器的双样本分类器来评估探测器层面的保真度；该分类器在 ROC 曲线下的面积为 $0.553 \pm 0.016$。训练后的模型生成事件的速度比 Geant4 快近四个数量级，为 FCC-ee 设计研究的快速模拟替代物铺平了道路。
英文摘要
Beam-induced backgrounds at high-luminosity $e^+e^-$ colliders, such as the FCC-ee, are dominated by incoherent pair creation (IPC), and require computationally expensive simulations with dedicated Monte Carlo (MC) event generators. Reliable detector and machine-detector interface studies necessitate event samples that are several orders of magnitude larger than what is practically attainable with existing MC. To alleviate this bottleneck, we present D$e^+e^-$ffusion, a denoising diffusion probabilistic model that operates as a permutation-equivariant, set-valued surrogate for fast IPC simulation. Trained on a small GuineaPig++ sample, D$e^+e^-$ffusion faithfully reproduces the marginal and joint kinematic, angular, and positional distributions of all three IPC production processes. In addition, we assess the fidelity at the detector level by propagating both Geant4 and D$e^+e^-$ffusion events through a Geant4 simulation of the CLD vertex detector and by training a transformer-based two-sample classifier; the classifier achieves an area under the ROC curve of $0.553 \pm 0.016$. The trained model generates events nearly four orders of magnitude faster than Geant4, paving the way for a fast-simulation surrogate for FCC-ee design studies.
Comments18 pages, 11 figures, and 1 table. Data and code are available at https://github.com/umarsqureshi/Deeffusion
