期刊
FOUNDATIONS OF COMPUTATIONAL MATHEMATICS
卷 22, 期 6, 页码 1863-1922出版社
SPRINGER
DOI: 10.1007/s10208-021-09537-5
关键词
Tensor-train; Inverse problems; Uncertainty quantification; Rosenblatt transport; Deep transport maps
资金
- Australian Research Council [CE140100049]
- International Visitor Program of Sydney Mathematical Research Institute
- EPSRC [EP/T031255/1]
This paper extends the functional tensor-train approximation of the inverse Rosenblatt transport to high-dimensional non-negative functions, develops an efficient procedure for computing the transport, and integrates it into a nested variable transformation framework. The resulting deep inverse Rosenblatt transport significantly expands the capability of tensor approximations and transport maps to handle random variables with complicated nonlinear interactions and concentrated density functions.
Characterising intractable high-dimensional random variables is one of the fundamental challenges in stochastic computation. The recent surge of transport maps offers a mathematical foundation and new insights for tackling this challenge by coupling intractable random variables with tractable reference random variables. This paper generalises the functional tensor-train approximation of the inverse Rosenblatt transport recently developed by Dolgov et al. (Stat Comput 30:603-625, 2020) to a wide class of high-dimensional non-negative functions, such as unnormalised probability density functions. First, we extend the inverse Rosenblatt transform to enable the transport to general reference measures other than the uniform measure. We develop an efficient procedure to compute this transport from a squared tensor-train decomposition which preserves the monotonicity. More crucially, we integrate the proposed order-preserving functional tensor-train transport into a nested variable transformation framework inspired by the layered structure of deep neural networks. The resulting deep inverse Rosenblatt transport significantly expands the capability of tensor approximations and transport maps to random variables with complicated nonlinear interactions and concentrated density functions. We demonstrate the efficiency of the proposed approach on a range of applications in statistical learning and uncertainty quantification, including parameter estimation for dynamical systems and inverse problems constrained by partial differential equations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据