We investigate enhancing the sensitivity of new physics searches at the LHC by machine learning in the case of background dominance and a high degree of overlap between the observables for signal and background. We use two different models, XGBoost and a deep neural network, to exploit correlations between observables and compare this approach to the traditional cut-and-count method. We consider different methods to analyze the models' output, finding that a template fit generally performs better than a simple cut. By means of a Shapley decomposition, we gain additional insight into the relationship between event kinematics and the machine learning model output. We consider a supersymmetric scenario with a metastable sneutrino as a concrete example, but the methodology can be applied to a much wider class of models.

翻译：我们研究了在背景主导且信号与背景可观测量高度重叠的情况下，利用机器学习提升大型强子对撞机（LHC）上新物理搜索灵敏度的方法。采用XGBoost与深度神经网络两种不同模型，通过利用可观测量之间的相关性，与传统计数法进行对比。通过分析模型输出的不同方法，我们发现模板拟合法通常优于简单阈值截断。借助沙普利分解，我们进一步揭示了事件运动学与机器学习模型输出之间的关联。本文以含亚稳态中微子的超对称场景为例进行具体分析，但该方法可推广至更广泛的模型类别。