论文标题
滑动窗口的窗帘：通过转换相邻间隔来构建未观察到的区域
CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
论文作者
论文摘要
我们提出了一种新的独立模型技术，用于构建背景数据模板，以用于搜索LHC的新物理过程。这种称为窗帘的方法使用可逆神经网络来参数侧带数据的分布，这是可观察到的谐振的函数。该网络将学习一个转换，以将任何数据点从可观察到的谐振值的值映射到另一个选择的值。使用窗帘，通过将数据从侧波段映射到信号区域的数据来构建信号窗口中背景数据的模板。我们使用窗帘背景模板执行异常检测，以增强撞击中对新物理的敏感性。我们在各种质量值范围内的滑动窗口搜索中演示了其性能。使用LHC奥运会数据集，我们证明了窗帘与其他领先方法的性能相匹配，这些方法旨在提高颠簸狩猎的敏感性，可以在不变质量的范围较小的范围内进行训练，并且完全由数据驱动。
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.
