Deep density estimation via invertible block-triangular mapping

Deep density estimation via invertible block-triangular mapping

ABSTRACT: 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:1605.08803v3). The triangula...

Full description

Bibliographic Details
Main Authors: Keju Tang, Xiaoliang Wan, Qifeng Liao
Format: Article
Language:English
Published: Elsevier 2020-03-01
Series:Theoretical and Applied Mechanics Letters
Subjects:
Deep learning
Density estimation
Optimal transport
Uncertainty quantification
Online Access:http://www.sciencedirect.com/science/article/pii/S209503492030026X

Similar Items

Similar Items