arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.06033stat.MLcs.LGstat.AP
收藏

从提升决策树中提取更多:高能物理案例研究

Extracting more from boosted decision trees: A high energy physics case study

University of Cambridge(剑桥大学);The Alan Turing Institute(艾伦·图灵研究所)

Vidhi Lalchand

摘要:

粒子识别是大型强子对撞机(LHC)数据分析流程中的核心任务之一。从统计学上讲,这需要识别隐藏在巨大背景中的罕见信号事件,这些背景模拟了前者的属性。在机器学习的说法中,粒子识别表示以重叠和不平衡的类为特征的分类问题。提升决策树(BDT)在粒子识别领域取得了巨大的成功,但最近被深度学习(DNN)方法所掩盖。这项工作提出了一种算法,以提取更多的标准提升决策树的主要弱点,过度拟合的敏感性。这种新颖的构造同时利用了提升和装袋的元学习技术,并且在ATLAS Higgs(H)到tau-tau数据集上表现得非常好(ATLAS等人,2014年),这是2014年希格斯ML挑战赛的主题(Adam-Bourdarios等人,2015)。虽然希格斯粒子衰变为一对τ轻子是在2018年建立的(CMS合作等,2017)在基于2016年数据采集期的4.9 $σ$显著性下,2014年公共数据集继续作为测试监督分类方案性能的基准数据集。我们表明,所提出的算法实现的分数是非常接近的出版的获奖分数,利用了集成的深度神经网络(DNN)。虽然本文侧重于一个单一的应用,预计这种简单而强大的技术将在高能物理中找到更广泛的应用。

英文摘要:

Particle identification is one of the core tasks in the data analysis pipeline at the Large Hadron Collider (LHC). Statistically, this entails the identification of rare signal events buried in immense backgrounds that mimic the properties of the former. In machine learning parlance, particle identification represents a classification problem characterized by overlapping and imbalanced classes. Boosted decision trees (BDTs) have had tremendous success in the particle identification domain but more recently have been overshadowed by deep learning (DNNs) approaches. This work proposes an algorithm to extract more out of standard boosted decision trees by targeting their main weakness, susceptibility to overfitting. This novel construction harnesses the meta-learning techniques of boosting and bagging simultaneously and performs remarkably well on the ATLAS Higgs (H) to tau-tau data set (ATLAS et al., 2014) which was the subject of the 2014 Higgs ML Challenge (Adam-Bourdarios et al., 2015). While the decay of Higgs to a pair of tau leptons was established in 2018 (CMS collaboration et al., 2017) at the 4.9$σ$ significance based on the 2016 data taking period, the 2014 public data set continues to serve as a benchmark data set to test the performance of supervised classification schemes. We show that the score achieved by the proposed algorithm is very close to the published winning score which leverages an ensemble of deep neural networks (DNNs). Although this paper focuses on a single application, it is expected that this simple and robust technique will find wider applications in high energy physics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑