A generalized Wasserstein-2 distance approach for efficient reconstruction of random field models using stochastic neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Mingtao, Shen, Qijing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909677595394048
author Xia, Mingtao
Shen, Qijing
author_facet Xia, Mingtao
Shen, Qijing
contents In this work, we propose a novel generalized Wasserstein-2 distance approach for efficiently training stochastic neural networks to reconstruct random field models, where the target random variable comprises both continuous and categorical components. We prove that a stochastic neural network can approximate random field models under a Wasserstein-2 distance metric under nonrestrictive conditions. Furthermore, this stochastic neural network can be efficiently trained by minimizing our proposed generalized local squared Wasserstein-2 loss function. We showcase the effectiveness of our proposed approach in various uncertainty quantification tasks, including classification, reconstructing the distribution of mixed random variables, and learning complex noisy dynamical systems from spatiotemporal data.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A generalized Wasserstein-2 distance approach for efficient reconstruction of random field models using stochastic neural networks
Xia, Mingtao
Shen, Qijing
Machine Learning
60A05, 68Q87, 65C99
In this work, we propose a novel generalized Wasserstein-2 distance approach for efficiently training stochastic neural networks to reconstruct random field models, where the target random variable comprises both continuous and categorical components. We prove that a stochastic neural network can approximate random field models under a Wasserstein-2 distance metric under nonrestrictive conditions. Furthermore, this stochastic neural network can be efficiently trained by minimizing our proposed generalized local squared Wasserstein-2 loss function. We showcase the effectiveness of our proposed approach in various uncertainty quantification tasks, including classification, reconstructing the distribution of mixed random variables, and learning complex noisy dynamical systems from spatiotemporal data.
title A generalized Wasserstein-2 distance approach for efficient reconstruction of random field models using stochastic neural networks
topic Machine Learning
60A05, 68Q87, 65C99
url https://arxiv.org/abs/2507.05143