Neural Implicit Solution Formula for Efficiently Solving Hamilton-Jacobi Equations

TL;DR

This paper introduces a deep learning-based implicit solution formula for Hamilton-Jacobi equations that is scalable to high dimensions and handles nonconvex Hamiltonians efficiently.

Contribution

It develops a novel implicit solution formula for HJ PDEs and a deep learning approach that bypasses traditional computational complexities, enabling high-dimensional problem solving.

Findings

Accurate solutions for high-dimensional HJ PDEs up to 40 dimensions.

Efficient handling of nonconvex Hamiltonians.

Scalable mesh-free deep learning methodology.

Abstract

This paper presents an implicit solution formula for the Hamilton-Jacobi partial differential equation (HJ PDE). The formula is derived using the method of characteristics and is shown to coincide with the Hopf and Lax formulas in the case where either the Hamiltonian or the initial function is convex. It provides a simple and efficient numerical approach for computing the viscosity solution of HJ PDEs, bypassing the need for the Legendre transform of the Hamiltonian or the initial condition, and the explicit computation of individual characteristic trajectories. A deep learning-based methodology is proposed to learn this implicit solution formula, leveraging the mesh-free nature of deep learning to ensure scalability for high-dimensional problems. Building upon this framework, an algorithm is developed that approximates the characteristic curves piecewise linearly for state-dependent Hamiltonians. Extensive experimental results demonstrate that the proposed method delivers highly accurate solutions, even for nonconvex Hamiltonians, and exhibits remarkable scalability, achieving computational efficiency for problems up to 40 dimensions.