Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE
SIAM Journal on Scientific Computing · 30.06.2026 · 48 (3) · C415-C452
DOI: 10.1137/24m1711480 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 04.05.2026. Verfasst von German Villalobos und 2 weiteren Autor:innen. Die Arbeit nennt 127 Literaturangaben. Gefördert von: National Science Foundation, Research Computing Data Core at the University of Houston, Pittsburgh Supercomputing Center Neocortex Spring 2023 Call.
Abstract (Originalsprache)
We investigate the use of neural networks (NNs) for the estimation of hidden model parameters and uncertainty quantification from noisy observational data for inverse parameter estimation problems. We formulate the parameter estimation as a Bayesian inverse problem. We consider a parametrized system of nonlinear ordinary differential equations (ODEs), which is the FitzHugh–Nagumo model. The considered problem exhibits significant mathematical and computational challenges for classical parameter estimation methods, including strong nonlinearities, nonconvexity, and sharp gradients. We explore how NNs overcome these challenges by approximating reconstruction maps for parameter estimation from observational data. The considered data are time series of the spiking membrane potential of a biological neuron. We infer parameters controlling the dynamics of the model, noise parameters of autocorrelated additive noise, and noise modeled via stochastic differential equations, as well as the covariance matrix of the posterior distribution to expose parameter uncertainties—all with just one forward evaluation of an appropriate NN. We report results for different NN architectures and study the influence of noise on prediction accuracy. We also report timing results for training NNs on dedicated hardware. Our results demonstrate that NNs are a versatile tool to estimate parameters of the dynamical system, stochastic processes, as well as uncertainties as they propagate though the governing ODE.
Förderung
- National Science Foundation
- Research Computing Data Core at the University of Houston
- Pittsburgh Supercomputing Center Neocortex Spring 2023 Call
Zitieren
APA
Villalobos, G., Rudi, J., & Mang, A. (2026). Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE. SIAM Journal on Scientific Computing, 48(3), C415-C452. https://doi.org/10.1137/24m1711480
Vancouver
Villalobos G, Rudi J, Mang A. Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE. SIAM Journal on Scientific Computing. 2026;48(3):C415-C452. doi:10.1137/24m1711480
BibTeX
@article{Villalobos2026,
author = {Villalobos, German and Rudi, Johann and Mang, Andreas},
title = {Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {3},
pages = {C415--C452},
doi = {10.1137/24m1711480}
}
EUVIMED