Skip to main navigation Skip to search Skip to main content

An analysis of the derivative-free loss method for solving PDEs

  • Dartmouth College

Research output: Contribution to journal › Article › peer-review

Abstract

This study analyzes the derivative-free loss method to solve a certain class of elliptic PDEs and fluid problems using neural networks. The approach leverages the Feynman–Kac formulation, incorporating stochastic walkers and their averaged values. We investigate how the time interval associated with the Feynman-Kac representation and the walker size influences computational efficiency, trainability, and sampling errors.Although the derivative-free method has demonstrated robustness in challenging settings, such as the homogenization of non-separable multiscale problems, domains with geometric singularities, and recent applications to fluid models, its theoretical foundations remain insufficiently understood. Such understanding is essential for principled parameter selection and stable training. Our analysis shows that the training loss is asymptotically unbiased, with a bias term that scales proportionally with the time interval and the spatial gradient of the neural network, while being inversely proportional to the walker size. Moreover, we demonstrate that the time interval must be sufficiently long to enable effective training. These results indicate that the walker size can be chosen as small as desired, provided it satisfies the optimal lower bound determined by the time interval. Finally, we present numerical experiments that support our theoretical findings.

Original languageEnglish
Article number47
JournalResearch in Mathematical Sciences
Volume13
Issue number2
DOIs
StatePublished - Jun 2026

Keywords

  • Bias estimation
  • Brownian sample
  • Derivative-free loss
  • Feynman–Kac formula

Fingerprint

Dive into the research topics of 'An analysis of the derivative-free loss method for solving PDEs'. Together they form a unique fingerprint.

Cite this