发表机构
MIT; NSF AI Institute for Artificial Intelligence and Fundamental Interactions（麻省理工学院; 美国国家科学基金会人工智能基础交互研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出协变对比学习框架，联合训练嵌入与参数化分类器，在潜在空间中建模连续系统不确定性，提升LHC异常检测的可解释性与鲁棒性。
AI 中文摘要
基于机器学习的异常检测（AD）为传统LHC分析提供了一种有前景的、模型无关的替代方案，允许同时搜索多种信号。表示学习的最新进展促使使用神经嵌入将高维物理观测量映射到更适合统计推断的低维潜在空间。然而，系统不确定性在嵌入空间中的传播仍未被充分理解，严重限制了这些方法在实际LHC分析中的应用。我们通过一种使用基于似然的正则化来改善嵌入空间结构的机器学习策略来解决这一差距。基于先前使用监督对比学习进行物理感知嵌入的工作，我们的方法将嵌入与下游参数化分类任务联合训练，该任务将连续不确定性作为 nuisance 参数纳入。该方法返回一个与系统偏移可预测地协变的潜在空间，以及一个可在下游异常检测统计检验中利用的此类畸变模型。使用模拟的CMS一级触发数据，我们展示了我们的方法成功地在4D潜在空间中用线性参数化下游分类器建模连续不确定性，提高了统计异常检测任务的可解释性和鲁棒性。该框架提供了一种在潜在空间中研究和控制系统不确定性的通用方法，为LHC及其他高能物理实验中的异常检测开辟了新的可扩展统计分析工作流程。
英文摘要
Machine-learning-based anomaly detection (AD) offers a promising, model-agnostic alternative to traditional LHC analyses, allowing to search for many signals at once. Recent advances in representation learning motivate the use of neural embeddings to map high-dimensional physics observables into low-dimensional latent spaces better suited to statistical inference. However, the propagation of systematic uncertainty in embedded spaces remains poorly understood, severely limiting the application of these methods to real LHC analyses. We address this gap with a machine learning strategy that uses a likelihood-based regularization to improve the structure of embedded spaces. Building on previous work using supervised contrastive learning for physics-aware embeddings, our approach trains them jointly with a downstream parameterized classification task that incorporates continuous uncertainties as nuisance parameters. This method returns a latent space that covaries predictably with systematic shifts, and a model of such distortions that can be exploited in the downstream statistical test for anomaly detection. Using simulated CMS Level-1 trigger data, we show that our method successfully models continuous uncertainties in a 4D latent space with a linear parametric downstream classifier, improving both the interpretability and robustness of the statistical anomaly detection task. This framework offers a general way to study and control systematic uncertainties in latent spaces, opening the way to a new scalable statistical analysis workflow for anomaly detection at the LHC, and other high energy physics experiments.
