arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11099hep-ph
收藏

使用深度学习校准的每对象系统学

Per-Object Systematics using Deep-Learned Calibration

Gregor Kasieczka, Michel Luchmann, Florian Otterpohl, Tilman Plehn

摘要:

我们展示了如何使用贝叶斯深度网络进行回归来处理系统不确定性。首先,我们分析了这些网络如何分别跟踪统计和系统的不确定性的动量助推顶夸克形成脂肪喷流。接下来,我们提出了一种新的校准过程,通过训练标签及其误差条。同样,网络清晰地分离了不同的不确定性。作为一个技术副作用,我们展示了贝叶斯网络如何扩展到描述非高斯特征。

英文摘要:

We show how to treat systematic uncertainties using Bayesian deep networks for regression. First, we analyze how these networks separately trace statistical and systematic uncertainties on the momenta of boosted top quarks forming fat jets. Next, we propose a novel calibration procedure by training on labels and their error bars. Again, the network cleanly separates the different uncertainties. As a technical side effect, we show how Bayesian networks can be extended to describe non-Gaussian features.

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。

↑