论文标题
与条件归一化流动相关
Decorrelation with conditional normalizing flows
论文作者
论文摘要
通过构建优先选择信号事件的判别因素，可以增强许多物理分析的敏感性。如果这种判别因素与一组受保护的属性不相关，它们会变得更有用。在本文中，我们表明，以保护属性为条件的归一化流程可用于为任何判别物找到非相关的表示形式。由于归一流的流程是可逆的，因此所得判别物的分离能力将在受保护属性的任何固定值下保持不变。我们通过构建有监督的喷气标签器来证明我们的方法的功效，这些标签机几乎没有在背景的质量分布中产生雕刻。
The sensitivity of many physics analyses can be enhanced by constructing discriminants that preferentially select signal events. Such discriminants become much more useful if they are uncorrelated with a set of protected attributes. In this paper we show that a normalizing flow conditioned on the protected attributes can be used to find a decorrelated representation for any discriminant. As a normalizing flow is invertible the separation power of the resulting discriminant will be unchanged at any fixed value of the protected attributes. We demonstrate the efficacy of our approach by building supervised jet taggers that produce almost no sculpting in the mass distribution of the background.
