Searching new physics with advanced data analysis techniques

在大型强子对撞机中，从大型标准模型背景中分离信号事件是一项极具挑战性的任务。学生将开发新的分析技术来完成这项任务。近年来，机器学习方法在信号和背景分离中利用运动特征变得越来越重要。Andrew将开发无监督学习算法的新技术，允许直接在数据上训练这些方法。然后，他将把这些方法应用到特定的新物理模型中，并评估在寻找标准模型的这种扩展时的灵敏度。

Separating signal events from large Standard Model backgrounds is a highly challenging task at the Large Hadron Collider. The student will develop novel analysis techniques to perform this task. In recent years machine-learning methods have become increasingly important to exploit kinematic features in the separation between signal and background. Andrew will develop new techniques for unsupervised learning algorithms which allows to train these methods directly on data. He will then apply these methods to specific new physics models and assess the sensitivity in searching for such extensions of the Standard Model.