规范化流是一类生成模型,可以进行精确的似然评估。虽然这些模型已经在粒子物理学中找到了各种应用,但归一化流不够灵活,无法模拟碰撞事件的许多外围特征。使用Nielsen et al.(2020)的框架,我们将几个满射和随机变换层引入基线归一化流,以改进排列对称性,不同维度和离散特征的建模,这些都是粒子物理事件中常见的。我们评估其效力的背景下生成的矩阵元素级的过程中,并在探测器级LHC事件的异常检测的背景下。
英文摘要:
Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the peripheral features of collision events. Using the framework of Nielsen et al. (2020), we introduce several surjective and stochastic transform layers to a baseline normalizing flow to improve modelling of permutation symmetry, varying dimensionality and discrete features, which are all commonly encountered in particle physics events. We assess their efficacy in the context of the generation of a matrix element-level process, and in the context of anomaly detection in detector-level LHC events.
Incorporating neutron star physics into gravitational wave inference with physics-informed priors using normalizing flows
Utrecht University(乌得勒支大学);Nikhef(尼黑国家粒子物理研究所);Universität Potsdam(波茨坦大学);Max Planck Institute for Gravitational Physics (Albert Einstein Institute)(马克斯·普朗克引力物理研究所(爱因斯坦研究所))
Ultra fast, event-by-event heavy-ion simulations for next generation experiments
Frankfurt Institute for Advanced Studies(法兰克福高等研究所);Xidian-FIAS International Joint Research Center(西电-法兰克福高等研究所国际联合研究中心);School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);GSI Helmholtzzentrum für Schwerionenforschung GmbH(德国重离子研究中心);Institut für Theoretische Physik, Goethe Universität Frankfurt(法兰克福歌德大学理论物理研究所)
Flows for Flows: Morphing one Dataset into another with Maximum Likelihood Estimation
Université de Genève(日内瓦大学);University of California, Berkeley(加利福尼亚大学伯克利分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Berkeley Institute for Data Science(伯克利数据科学研究所)
提出名为flows for flows的协议,利用极大似然估计训练normalizing flows,在未知概率密度的情况下将一个数据集变换为另一个,并支持特征条件化,应用于高能物理等数据集变换任务。