arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.13632hep-phcs.LG
收藏

面向精度爱好者的生成网络

Generative Networks for Precision Enthusiasts

Universität Heidelberg(海德堡大学)

Anja Butter, Theo Heimel, Sander Hummerich, Tobias Krebs, Tilman Plehn, Armand Rousselot, Sophia Vent

AI总结:

本文提出生成流网络与判别器的新型联合训练方法,用于LHC快速事例生成,可使运动学分布达到百分比级精度,并通过贝叶斯网络和条件数据增强估计不确定性。

摘要:

生成网络正在为大型强子对撞机(LHC)的快速事例生成开辟新途径。我们展示了生成流网络如何在运动学分布上达到百分比级精度,如何与判别器联合训练,以及该判别器如何改进生成。我们的联合训练依赖于两个网络之间一种新颖的耦合方式,且不需要纳什均衡。随后,我们通过贝叶斯网络设置和条件数据增强来估计生成不确定性,同时判别器确保与训练数据相比不存在系统性不一致。

英文摘要:

Generative networks are opening new avenues in fast event generation for the LHC. We show how generative flow networks can reach percent-level precision for kinematic distributions, how they can be trained jointly with a discriminator, and how this discriminator improves the generation. Our joint training relies on a novel coupling of the two networks which does not require a Nash equilibrium. We then estimate the generation uncertainties through a Bayesian network setup and through conditional data augmentation, while the discriminator ensures that there are no systematic inconsistencies compared to the training data.

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。

↑