混合密度网络用于强子对撞机中微子重建
Mixture Density Networks for Neutrino Reconstruction at Hadron Colliders
浏览论文内容
中文总结 AI 辅助
针对强子对撞机中微子动量重建的固有歧义，提出基于Transformer事件编码的混合密度网络\monster{}，在公开基准上较归一化流基线降低残差百分位并提速，验证其作为归一化流替代方案的竞争力。
中文摘要 AI 辅助
在强子对撞机中，中微子动量重建本质上存在歧义，因为纵向动量无法直接观测。我们利用\monster{}（混合中微子解与Transformer事件表示）研究半轻子$t\bar{t}$事件中的这一问题。\monster{}是一种混合密度网络，它从重建的事件对象中预测中微子动量的条件分布，该分布为多元正态混合。该模型采用基于Transformer的事件编码器，并通过闭式密度提供无采样的中微子动量点估计。在\nuflows{}引入的公开基准上，相对于经验众数\nuflows{}基线，\monster{}将三动量残差的第68百分位降低了5%，第95百分位降低了6%，在可比偏差下，各变量的均方根误差减小了2%至9%，同时根据设备和批大小，推理速度提高了2至8.5倍。这些结果表明，混合密度网络是中微子重建中归一化流的一个有竞争力的替代方案。
英文摘要
Neutrino momentum reconstruction at hadron colliders is intrinsically ambiguous because the longitudinal momentum is not directly observed. We study this problem in semileptonic $t\bar{t}$ events using \monster{} (Mixture of Neutrino Solutions with Transformer Event Representation), a mixture density network that predicts a multivariate normal mixture for the conditional distribution of neutrino momentum from reconstructed event objects. The model uses a Transformer-based event encoder and yields a sampling-free point estimate of the neutrino momentum from the closed-form density. On the public benchmark introduced with \nuflows, \monster{} reduces the 68th percentile of the three-momentum residual by 5\% and the 95th percentile by 6\% relative to the empirical-mode \nuflows{} baseline, with per-variable root-mean-square errors smaller by 2 to 9\% at comparable bias, while running 2 to 8.5 times faster at inference, depending on the device and batch size. These results indicate that mixture density networks are a competitive alternative to normalizing flows for neutrino reconstruction.
发表机构
- University of Seoul（首尔大学）
- Yonsei University（延世大学）
- Kyung Hee University（庆熙大学）
机构由 AI 辅助整理，请以论文原文为准。
