Finite-difference least square methods for solving Hamilton-Jacobi equations using neural networks

2024/06/15 by Carlos Esteve, Esteve-Yagüe, Carlos, Richard Tzong‐Han Tsai +3
Computer Science · #35A15 #49K20 #49L25 #65N06 #68T07 #Analysis of PDEs (math.AP) #FOS: Mathematics #Neural Networks and Applications #Numerical Analysis (math.NA) #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2406.10758

openalex publication_date 2024/06/15 · openalex created_date 2024/06/20 · openalex updated_date 2026/07/28

Abstract

We present a simple algorithm to approximate the viscosity solution of Hamilton-Jacobi (HJ) equations by means of an artificial deep neural network. The algorithm uses a stochastic gradient descent-based method to minimize the least square principle defined by a monotone, consistent numerical scheme. We analyze the least square principle's critical points and derive conditions that guarantee that any critical point approximates the sought viscosity solution. The use of a deep artificial neural network on a finite difference scheme lifts the restriction of conventional finite difference methods that rely on computing functions on a fixed grid. This feature makes it possible to solve HJ equations posed in higher dimensions where conventional methods are infeasible. We demonstrate the efficacy of our algorithm through numerical studies on various canonical HJ equations across different dimensions, showcasing its potential and versatility.

Related

• Neural Implicit Solution Formula for Efficiently Solving Hamilton-Jacobi Equations
• Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
• Using Neural Networks to Compute Approximate and Guaranteed Feasible Hamilton-Jacobi-Bellman PDE Solutions
• Deep Relaxation: partial differential equations for optimizing deep\n neural networks
• Three Ways to Solve Partial Differential Equations with Neural Networks\n -- A Review