arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.06307hep-phhep-exphysics.comp-phphysics.data-an
收藏

高能物理中与GAN生成的数据集相关的不确定性

Uncertainties associated with GAN-generated datasets in high energy physics

Konstantin T. Matchev, Alexander Roman, Prasanth Shyamsundar

备注：
28 pages, 11 figures. Revised submission to SciPost
发表信息：
SciPost Phys. 12, 104 (2022)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

最近，生成对抗网络（GANs）在传统模拟的对撞机事件的样本上进行训练，作为一种以降低的计算成本生成更大的模拟数据集的方法。在本文中，我们指出，GAN生成的数据在统计上不可能比它训练的数据更好，并严格审查了GANs在各种情况下的适用性，包括a）替换整个Monte Carlo管道或部分管道，以及b）生成用于高度敏感分析或次优分析的数据集。我们提出我们的论点，使用信息理论的演示，一个玩具的例子，以及在一个正式的声明的形式，并确定一些潜在的有效使用的GANs在对撞机模拟。

英文摘要：

Recently, Generative Adversarial Networks (GANs) trained on samples of traditionally simulated collider events have been proposed as a way of generating larger simulated datasets at a reduced computational cost. In this paper we point out that data generated by a GAN cannot statistically be better than the data it was trained on, and critically examine the applicability of GANs in various situations, including a) for replacing the entire Monte Carlo pipeline or parts of it, and b) to produce datasets for usage in highly sensitive analyses or sub-optimal ones. We present our arguments using information theoretic demonstrations, a toy example, as well as in the form of a formal statement, and identify some potential valid uses of GANs in collider simulations.

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。

↑