Bayesian hyper-parameter optimization of physics-informed neural networks to a nonlocal nonlinear Schrödinger equation
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.06.2026 · 36 (6)
DOI: 10.1063/5.0311385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 02.06.2026. Verfasst von Lianghui Hou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Zhejiang Sci-Tech University, Hangzhou 310018, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
In previous applications of a physical information neural networks (PINN) algorithm, the adjustment of hyper-parameter combinations for neural networks has predominantly been conducted manually. This manual configuration strategy often suffers from inefficiency, and it cannot guarantee that the network trained with such parameters can achieve optimal performance. To address the hyper-parameter tuning challenge of PINNs, this paper is devoted to introducing a Bayesian hyper-parameter optimization method for PINN (BHPO-PINN) based on a Gaussian process. This approach enhances training performance by identifying optimal combinations of different hyper-parameters and is further applied to solve the nonlocal reverse-time nonlinear Schrödinger equation. Numerical simulations of a data-driven one-soliton solution and four types of two-soliton solutions are performed, and systematic comparative analyses of relative errors and maximum absolute errors are presented to quantify the solution accuracy. To identify the optimal combination of network hyper-parameters, we conduct a thorough investigation by analyzing error variations under different training iterations. The experimental results demonstrate that the BHPO-PINN method achieves significantly enhanced accuracy and stability compared to the traditional PINN algorithm under empirically configured hyper-parameters.
Autor:innen und Institutionen
- Department of Mathematics, Zhejiang Sci-Tech University, Hangzhou 310018, China.
- Department of Mathematics, Lishui University, Lishui 323000, China.
- Zhejiang Provincial Collaborative Innovation Center of Visual Intelligent and Lean-oriented Manufacturing, Lishui University, Lishui 323000, China.
ORCID-Profile: Lianghui Hou, Junchao Chen
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
Zitieren
APA
Hou, L., Cheng, L., Yang, Y., & Chen, J. (2026). Bayesian hyper-parameter optimization of physics-informed neural networks to a nonlocal nonlinear Schrödinger equation. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(6). https://doi.org/10.1063/5.0311385
Vancouver
Hou L, Cheng L, Yang Y, Chen J. Bayesian hyper-parameter optimization of physics-informed neural networks to a nonlocal nonlinear Schrödinger equation. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(6). doi:10.1063/5.0311385
BibTeX
@article{Hou2026,
author = {Hou, Lianghui and Cheng, Li and Yang, Yi and Chen, Junchao},
title = {Bayesian hyper-parameter optimization of physics-informed neural networks to a nonlocal nonlinear Schrödinger equation},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {6},
doi = {10.1063/5.0311385}
}
EUVIMED