大型强子对撞机异常检测中针对背景塑形的域适应
Domain Adaptation against Background Sculpting in Anomaly Detection at the LHC
浏览论文内容
中文总结 AI 辅助
针对LHC异常检测中背景塑形问题，提出基于域适应的去相关方法，在保持检测性能的同时显著减少背景扭曲，并恢复灵敏度。
中文摘要 AI 辅助
弱监督异常检测已被证明是模型无关的新物理搜索的有效工具，尤其是在共振搜索的背景下。然而，异常分数与共振质量之间的相关性会在选择异常分数后扭曲背景分布，从而使从侧带估计背景变得复杂。为了缓解这种背景塑形，我们提出了一种基于域适应的去相关方法，将异常分数与共振质量去相关。我们使用LHC Olympics R&D数据集和几种弱监督异常检测方法研究了这种方法。我们发现，域适应可以显著减少背景塑形，同时在很大程度上保持异常检测性能。当输入特征与共振质量之间的相关性降低了原始方法的性能时，域适应还可以恢复灵敏度。
英文摘要
Weakly supervised anomaly detection has been shown to be an effective tool for model-agnostic searches for new physics, especially in the context of resonance searches. However, correlations between the anomaly score and the resonant mass can distort the background distribution after selecting on the anomaly score, complicating background estimation from the sidebands. To mitigate this background sculpting, we propose a domain-adaptation-based decorrelation of the anomaly score from the resonant mass. We study this approach using the LHC Olympics R&D data set and several weakly supervised anomaly detection methods. We find that domain adaptation can substantially reduce background sculpting while largely preserving the anomaly detection performance. When correlations between the input features and the resonant mass degrade the original method's performance, domain adaptation can also recover sensitivity.
发表机构
- RWTH Aachen University（亚琛工业大学）
- ETH Zürich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。
