Deep density estimation via invertible block-triangular mapping

Keju Tang

doi:10.1016/j.taml.2020.01.023

Deep density estimation via invertible block-triangular mapping

2020-03-01

14

OA

AI

DOI：10.1016/j.taml.2020.01.023

原文链接

查看原文

摘要

En 中文

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 triangular structure of the KR rearrangement breaks the symmetry of the real NVP in terms of the exchange of information between dimensions, which not only accelerates the training process but also improves the accuracy significantly. We have also introduced several new layers into the generative model to improve both robustness and effectiveness, including a reformulated affine coupling layer, a rotation layer and a component-wise nonlinear invertible layer. The KRnet can be used for both density estimation and sample generation especially when the dimensionality is relatively high. Numerical experiments have been presented to demonstrate the performance of KRnet. (c) 2020 The Authors. Published by Elsevier Ltd on behalf of The Chinese Society of Theoretical and Applied Mechanics.

Keyword:

Deep learning

Density estimation

Optimal transport

Uncertainty quantification

Deep density estimation via invertible block-triangular mapping

摘要

AI总结

期刊

机构

引用论文