Holistic approach to predicting top quark kinematic properties with the covariant particle transformer
Holistic approach to predicting top quark kinematic properties with the covariant particle transformer
复制标题
DOI：
10.1103/physrevd.107.114029
复制
发表时间：
2022-03
影响因子：
5
通讯作者：
Shikai Qiu;Shuo Han;X. Ju;B. Nachman;Haichen Wang
中科院分区：
文献类型：
--
作者：
Shikai Qiu;Shuo Han;X. Ju;B. Nachman;Haichen Wang
由于组合背景和信息缺失，在大型强子对撞机上精确重建顶夸克性质是一项具有挑战性的任务。我们引入了一种被称为协变粒子变压器（CPT）的物理信息神经网络架构，用于直接预测重构最终状态对象的顶夸克运动特性。这种方法是排列不变和部分洛伦兹协变的，并且可以解释可变数量的输入对象。与之前基于机器学习的重建方法相比，CPT能够预测顶夸克四动量，而不考虑事件中的喷流多重性。通过模拟，我们表明与其他机器学习顶夸克重建方法相比，CPT表现良好。
Precise reconstruction of top quark properties is a challenging task at the Large Hadron Collider due to combinatorial backgrounds and missing information. We introduce a physics-informed neural network architecture called the Covariant Particle Transformer (CPT) for directly predicting the top quark kinematic properties from reconstructed final state objects. This approach is permutation invariant and partially Lorentz covariant and can account for a variable number of input objects. In contrast to previous machine learning-based reconstruction methods, CPT is able to predict top quark four-momenta regardless of the jet multiplicity in the event. Using simulations, we show that the CPT performs favorably compared with other machine learning top quark reconstruction approaches.