arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07674hep-phhep-ex
收藏

在LHC上从$U(1)_{L_μ-L_τ}$对$Z'$进行机器学习优化搜索

Machine Learning Optimized Search for the $Z'$ from $U(1)_{L_μ-L_τ}$ at the LHC

Manuel Drees, Meng Shi, Zhongyi Zhang

摘要:

扩展标准模型(SM)的$U(1)_{L_μ-L_τ}$组提供了潜在的重大新的贡献,$g_μ-2$,允许现实的中微子质量矩阵的建设,结合轻子普适性破坏,并提供了一个无异常介质的暗物质(DM)部门。在最近的一项分析中,我们发现已发表的LHC搜索对这个模型并不敏感。在这里,我们应用了几种机器学习(ML)算法,以便使用模拟LHC数据将该模型与SM区分开来。特别是,我们优化了$3μ$ -信号,它具有比$4μ$ -信号大得多的横截面。此外,由于$2$ -μ子加上丢失的$E_T$末态得到了涉及DM粒子的图的贡献,我们也对其进行了优化。我们发现大大提高了灵敏度,这已经为$36$ fb $^{-1}$的数据超过了已发表的LHC和非LHC结果的组合。我们还强调了提升决策树的有用性,与神经网络不同,它可以轻松地从数据中提取额外的信息,这些信息通过特征重要性直接连接到理论模型。同样的方法也可以用于其他模型的分析。

英文摘要:

Extending the Standard Model (SM) by a $U(1)_{L_μ-L_τ}$ group gives potentially significant new contributions to $g_μ-2$, allows the construction of realistic neutrino mass matrices, incorporates lepton universality violation, and offers an anomaly-free mediator for a Dark Matter (DM) sector. In a recent analysis we showed that published LHC searches are not very sensitive to this model. Here we apply several Machine Learning (ML) algorithms in order to distinguish this model from the SM using simulated LHC data. In particular, we optimize the $3μ$-signal, which has a considerably larger cross section than the $4μ$-signal. Furthermore, since the $2$-muon plus missing $E_T$ final state gets contributions from diagrams involving DM particles, we optimize it as well. We find greatly improved sensitivity, which already for $36$ fb$^{-1}$ of data exceeds the combination of published LHC and non-LHC results. We also emphasize the usefulness of Boosted Decision Trees which, unlike Neural Networks, easily allow to extract additional information from the data which directly connect to the theoretical model through feature importance. The same scheme could be used to analyze other models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑