EUVIMEDEUVIMED entdecken
Crossref

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations

Zheyuan Hu, Zhongqiang Zhang, George E. Karniadakis, Kenji Kawaguchi

SIAM Journal on Scientific Computing · 30.06.2025 · 47 (3) · C680-C705

DOI: 10.1137/24m1638768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 06.06.2025. Verfasst von Zheyuan Hu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 48 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Fokker–Planck (FP) equation is a foundational partial differential equation (PDE) in stochastic processes involving Brownian motions. However, the curse of dimensionality (CoD) poses a formidable challenge when dealing with high-dimensional FP equations. Although Monte Carlo simulation and (vanilla) Physics-Informed Neural Networks (PINNs) have shown the potential to tackle CoD, both methods exhibit significant numerical errors in high dimensions when dealing with the probability density function (PDF) associated with Brownian motion. The pointwise PDF values tend to decrease exponentially as dimensionality increases, surpassing the precision of numerical simulations and resulting in substantial errors. Moreover, due to its massive sampling, Monte Carlo fails to offer fast sampling. Modeling the logarithm likelihood (LL) via vanilla PINNs transforms the FP equation into a notoriously difficult Hamilton–Jacobi–Bellman (HJB) equation, which is impractical for PINN learning, whose error grows rapidly with dimension. To this end, we propose a novel approach utilizing a score-based solver to fit the score function in stochastic differential equations (SDEs). The score function, defined as the gradient of the LL, plays a fundamental role in inferring LL and PDF and enables fast SDE sampling, offering an effective means to overcome the CoD. Three fitting methods, Score Matching (SM), Sliced Score Matching (SSM), and Score-PINN, are introduced, each contributing unique advantages in computational complexity, accuracy, and generality. The proposed score-based SDE solver operates in two stages: first, employing SM or Score-PINN to acquire the score function; and second, solving the LL via an ordinary differential equation (ODE) using the obtained score function. Comparative evaluations across these methods showcase varying tradeoffs. The proposed methodology is evaluated across diverse SDEs, including anisotropic Ornstein–Uhlenbeck processes, geometric Brownian motion, and Brownian motion with varying eigenspace. We also test various distributions, including Gaussian, Log-normal, Laplace, and Cauchy distributions. The numerical results demonstrate the score-based SDE solver’s stability, speed, and performance across different experimental settings, solidifying its potential as a solution to CoD for high-dimensional FP equations. Our code is available at https://github.com/zheyuanhu01/Score_PINN . Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/zheyuanhu01/Score_PINN and in the supplementary material ( Score_PINN-main.zip [17KB]). [Formula: see text]

Zitieren

APA

Hu, Z., Zhang, Z., Karniadakis, G. E., & Kawaguchi, K. (2025). Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations. SIAM Journal on Scientific Computing, 47(3), C680-C705. https://doi.org/10.1137/24m1638768

Vancouver

Hu Z, Zhang Z, Karniadakis GE, Kawaguchi K. Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations. SIAM Journal on Scientific Computing. 2025;47(3):C680-C705. doi:10.1137/24m1638768

BibTeX
@article{Hu2025,
  author = {Hu, Zheyuan and Zhang, Zhongqiang and Karniadakis, George E. and Kawaguchi, Kenji},
  title = {Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations},
  journal = {SIAM Journal on Scientific Computing},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {C680--C705},
  doi = {10.1137/24m1638768}
}
Kostenlos starten →