机器可自动发现参数函数以对高能物理数据建模
Machine Can Automatically Discover Parametric Functions to Model HEP Data
浏览论文内容
中文总结 AI 辅助
研究高能物理数据分析中为分箱数据找合适函数建模的问题,核心方法是用符号回归实现自动化,主要贡献是展示SymbolFit软件包,在双喷注谱演示中取得良好效果,如生成众多拟合函数,部分运行重新发现已用函数。
中文摘要 AI 辅助
在高能物理数据分析中,为分箱数据找到合适的函数建模很大程度上依赖手工过程:凭直觉猜测函数形式、拟合、检查,然后重复直至成功。我们表明,这个迭代过程可用符号回归实现自动化,它在函数空间进行数据驱动搜索,无需事先知道合适函数的样子。我们展示了SymbolFit软件包,它将符号回归与不确定性建模结合用于高能物理分析用例,并在CMS和ATLAS Run 2双喷注谱上进行了演示:在七种简单拟合配置下的560次独立种子运行生成了1000多个拟合谱的函数,其中111次运行重新发现了已发表双喷注搜索中使用的双喷注和UA2函数。
英文摘要
In HEP data analyses, finding an adequate function to model binned data has largely relied on a manual process: guess a functional form by intuition, fit, examine, then repeat until successful. We show that this iterative process can be automated by a machine using symbolic regression, which performs a data-driven search over function space without requiring prior knowledge of what an adequate function should look like. We present the SymbolFit package, which pairs symbolic regression with uncertainty modeling to target HEP analysis use cases, and demonstrate it on the CMS and ATLAS Run 2 dijet spectra: 560 independent seeded runs across seven simple fit configurations generated over 1000 functions fitting the spectra with $χ^2/\text{NDF}\approx 1$, and 111 of the runs rediscovered the very dijet and UA2 functions used in published dijet searches.
发表机构
- University of Pennsylvania, USA(宾夕法尼亚大学)
- European Organization for Nuclear Research (CERN), Switzerland(欧洲核子研究中心)
- University of Cambridge, UK(剑桥大学)
- University of Wisconsin-Madison, USA(威斯康星大学麦迪逊分校)
- University of California San Diego, USA(加州大学圣地亚哥分校)
- Massachusetts Institute of Technology, USA(麻省理工学院)
- Institute for Artificial Intelligence(人工智能研究所)
机构由 AI 辅助整理,请以论文原文为准。