Deep density estimation via invertible block-triangular mapping

• 作 者: Keju Tang Xiaoliang Wan Qifeng
• 机 构: SchoolofInformationScienceandTechnology,DepartmentofMathematicsandCenterforComputationandTechnology
• 出 处: 力学快报:英文版
• 发表日期: 2020年3期
• 关键词: Deep learning Density estimation Optimal transport Uncertainty quantification
• 基金项目: supported by the National Natural Science Foundation of Unite States (Grants DMS-1620026 and DMS-1913163),supported by the National Natural Science Foundation of China (Grant 11601329)

In this work,we develop an invertible transport map,called KRnet,for density estimation by coupling the Knothe–Rosenblatt(KR)rearrangement and the flow-based generative model,which generalizes the real-valued non-volume preserving(real NVP)model(arX-iv:16