Enhancing searches for resonances with machine learning and moment decomposition
Enhancing searches for resonances with machine learning and moment decomposition
复制标题
DOI：
10.1007/jhep04(2021)070
复制
发表时间：
2020-10
影响因子：
5.4
通讯作者：
O. Kitouni;B. Nachman;C. Weisser;Mike Williams
中科院分区：
文献类型：
--
作者：
O. Kitouni;B. Nachman;C. Weisser;Mike Williams
寻找共振新物理学的一个关键挑战是，经过训练以增强潜在信号的分类器必须不诱导局部结构。当使用边带方法从数据估计背景时，这种结构可能导致错误信号。已经开发了各种技术来构建独立于共振特征（通常是质量）的分类器。这样的策略足以避免局部化结构，但不是必需的。我们开发了一套新的工具，使用一种新的矩损失函数（矩分解或M o D e），放松了独立性的假设，而无需在背景中创建结构。通过允许分类器更灵活，我们提高了对新物理的敏感性，而不会影响背景估计的保真度。
A key challenge in searches for resonant new physics is that classifiers trained to enhance potential signals must not induce localized structures. Such structures could result in a false signal when the background is estimated from data using sideband methods. A variety of techniques have been developed to construct classifiers which are independent from the resonant feature (often a mass). Such strategies are sufficient to avoid localized structures, but are not necessary. We develop a new set of tools using a novel moment loss function (Moment Decomposition or M o D e) which relax the assumption of independence without creating structures in the background. By allowing classifiers to be more flexible, we enhance the sensitivity to new physics without compromising the fidelity of the background estimation.