论文标题
改善高能物理（及以后）的参数神经网络
Improving Parametric Neural Networks for High-Energy Physics (and Beyond)
论文作者
论文摘要
信号背景分类是高能物理（HEP）中的一个核心问题，它在发现新的基本颗粒方面起着重要作用。最近的方法 - 参数神经网络（PNN） - 利用多个信号质量假设作为额外的输入特征，以有效地替换一组单个分类器，每个分类器（原则上）为相应的质量假设提供了最佳响应。在这项工作中，我们旨在根据现实世界的使用来加深对PNN的理解。我们发现了几个参数网络的特殊性，为它们提供了直觉，指标和指南。我们进一步提出了一种替代参数化方案，从而产生了新的参数化神经网络体系结构：仿射；以及许多其他通常适用的改进，例如平衡培训程序。最后，我们在此处首次在此处提供的不平衡版本（称为hepmass-imb）在Hepmass数据集上进行了广泛和经验评估我们的模型，以进一步验证我们的方法。前提是结果也取决于提议的设计决策，分类性能和插值能力的影响。
Signal-background classification is a central problem in High-Energy Physics (HEP), that plays a major role for the discovery of new fundamental particles. A recent method -- the Parametric Neural Network (pNN) -- leverages multiple signal mass hypotheses as an additional input feature to effectively replace a whole set of individual classifiers, each providing (in principle) the best response for the corresponding mass hypothesis. In this work we aim at deepening the understanding of pNNs in light of real-world usage. We discovered several peculiarities of parametric networks, providing intuition, metrics, and guidelines to them. We further propose an alternative parametrization scheme, resulting in a new parametrized neural network architecture: the AffinePNN; along with many other generally applicable improvements, like the balanced training procedure. Finally, we extensively and empirically evaluate our models on the HEPMASS dataset, along its imbalanced version (called HEPMASS-IMB) we provide here for the first time, to further validate our approach. Provided results are in terms of the impact of the proposed design decisions, classification performance, and interpolation capability, as well.
