用于 ttH 多轻子信号灵敏度的机器学习架构基准测试
Benchmarking Machine Learning Architectures for ttH Multilepton Signal Sensitivity
浏览论文内容
中文总结 AI 辅助
该研究针对 ttH 多轻子信号灵敏度，提出合成数据集，对多种机器学习模型进行系统评估。通过标准化程序和构建特征集层次结构，比较模型性能，确立了粒子变压器和 LorentzNet 的优越性，并指出改进方向，结论有望推广。
中文摘要 AI 辅助
高能物理中信号发现和信号强度估计的统计测试越来越依赖于在模拟数据上训练的机器学习模型。我们提出了一个用于 t tH 多轻子信号 - 背景分类的合成数据集，并对从广泛用于表格数据的 XGBoost 到处理具有内置洛伦兹对称性事件的 LorentzNet 等机器学习模型进行了系统评估。现有研究在特征定义、训练过程和评估指标上常常不同，难以分离模型架构对性能的影响。为此，我们应用标准化训练和超参数优化程序，构建受控的特征集层次结构，并对模型进行全面比较。除了信号强度不确定性这一分析驱动指标外，我们还报告了常用的 ROC AUC 指标，并表明在实际加权训练下，它与基于不确定性的模型排名相关性良好。我们进一步研究了模型性能作为输入特征集、训练集大小以及特定通道和统一多通道训练选择的函数。我们的结果确立了粒子变压器和 LorentzNet 在考虑设置中的优越性。我们还确定了进一步改进的潜在途径，包括更具表现力的架构、跨附加分析通道的联合训练以及更大的模拟数据集。尽管本研究专注于特定的希格斯玻色子分析，但我们预计主要结论可推广到 LHC 和 HL - LHC 更广泛的搜索和测量类别。
英文摘要
Statistical testing for signal discovery and signal-strength estimation in high-energy physics increasingly relies on machine-learning models trained on simulated data. We present a synthetic dataset for $t\bar t H$ multilepton signal--background classification and perform a systematic evaluation of machine-learning models ranging from the widely used XGBoost for tabular data to LorentzNet, which processes events with built-in Lorentz symmetry. Existing studies often differ in feature definitions, training procedures, and evaluation metrics, making it difficult to isolate the impact of model architecture on performance. To address this, we apply standardized training and hyperparameter-optimization procedures, construct a controlled hierarchy of feature sets, and perform a comprehensive comparison of the models. In addition to the analysis-driven metric of signal-strength uncertainty, we report the commonly used ROC AUC metric and show that under realistically weighted training, it correlates well with the uncertainty-based ranking of models. We further investigate model performance as a function of input feature set, training-set size, and the choice between channel-specific and unified multi-channel training. Our results establish the superiority of Particle Transformer and LorentzNet within the considered setup. We also identify potential avenues for further improvement, including more expressive architectures, joint training across additional analysis channels, and larger simulated datasets. Although this study focuses on a specific Higgs-boson analysis, we expect the main conclusions to generalize to a broader class of searches and measurements at the LHC and HL-LHC.
