A supervised learning scheme for computing Hamilton-Jacobi equation via density coupling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Jianbo, Liu, Shu, Zhou, Haomin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909886236852224
author Cui, Jianbo
Liu, Shu
Zhou, Haomin
author_facet Cui, Jianbo
Liu, Shu
Zhou, Haomin
contents We propose a supervised learning scheme for the first order Hamilton--Jacobi PDEs in high dimensions. The scheme is designed by using the geometric structure of Wasserstein Hamiltonian flows via a density coupling strategy. It is equivalently posed as a regression problem using the Bregman divergence, which provides the loss function in learning while the data is generated through the particle formulation of Wasserstein Hamiltonian flow. We prove a posterior estimate on $L^1$ residual of the proposed scheme based on the coupling density. Furthermore, the proposed scheme can be used to describe the behaviors of Hamilton--Jacobi PDEs beyond the singularity formations on the support of coupling density. Several numerical examples with different Hamiltonians are provided to support our findings.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A supervised learning scheme for computing Hamilton-Jacobi equation via density coupling
Cui, Jianbo
Liu, Shu
Zhou, Haomin
Numerical Analysis
65M75, 65P10, 49Q22, 68T07
We propose a supervised learning scheme for the first order Hamilton--Jacobi PDEs in high dimensions. The scheme is designed by using the geometric structure of Wasserstein Hamiltonian flows via a density coupling strategy. It is equivalently posed as a regression problem using the Bregman divergence, which provides the loss function in learning while the data is generated through the particle formulation of Wasserstein Hamiltonian flow. We prove a posterior estimate on $L^1$ residual of the proposed scheme based on the coupling density. Furthermore, the proposed scheme can be used to describe the behaviors of Hamilton--Jacobi PDEs beyond the singularity formations on the support of coupling density. Several numerical examples with different Hamiltonians are provided to support our findings.
title A supervised learning scheme for computing Hamilton-Jacobi equation via density coupling
topic Numerical Analysis
65M75, 65P10, 49Q22, 68T07
url https://arxiv.org/abs/2401.15954