滑动窗口的CURTANs：通过变换相邻区间构造未观测区域
CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
摘要：
我们提出了一种新的模型无关的技术，用于构建背景数据模板，用于搜索新的物理过程在大型强子对撞机。这种方法称为CURTAINS，使用可逆神经网络来参数化边带数据的分布，作为共振可观测值的函数。网络学习一种变换，将任何数据点从其共振可观测值映射到另一个选定值。使用CURTAINS，通过将来自边带的数据映射到信号区域来构造信号窗口中的背景数据的模板。我们使用CURTAINS背景模板进行异常检测，以提高对碰撞搜索中新物理的敏感性。我们展示了它的性能在一个滑动窗口搜索范围广泛的质量值。使用LHC Olympics数据集，我们证明了CURTAINS与其他领先方法的性能相匹配，这些方法旨在提高碰撞搜索的灵敏度，可以在更小的不变质量范围内进行训练，并且完全是数据驱动的。
英文摘要：
We propose a new model independent technique for constructing background data templates for use in searches for new physics processes at the LHC. This method, called CURTAINs, uses invertible neural networks to parametrise the distribution of side band data as a function of the resonant observable. The network learns a transformation to map any data point from its value of the resonant observable to another chosen value. Using CURTAINs, a template for the background data in the signal window is constructed by mapping the data from the side-bands into the signal region. We perform anomaly detection using the CURTAINs background template to enhance the sensitivity to new physics in a bump hunt. We demonstrate its performance in a sliding window search across a wide range of mass values. Using the LHC Olympics dataset, we demonstrate that CURTAINs matches the performance of other leading approaches which aim to improve the sensitivity of bump hunts, can be trained on a much smaller range of the invariant mass, and is fully data driven.
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。
