mlsanityData to 14 Oct 2026

Bayesian Reasoning for Physics Informed Neural Networks

arXiv 2308.13222 ↗First posted 25 Aug 2023physics.comp-ph cs.LG physics.flu-dyncited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN approaches based on sampling or variational inference, the proposed method uses a Laplace approximation to compute model evidence analytically, enabling efficient hyperparameter tuning and model comparison without posterior sampling. We demonstrate the method on the heat, wave, and Burgers' equations, obtaining solutions in agreement with exact or reference results. In the Burgers' equation example, we further show that the framework naturally integrates information from governing equations and noisy measurements, providing predictive uncertainties within a unified Bayesian setting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 78 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

32 of 78 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  4. 2017DGM: A deep learning algorithm for solving partial differential equationscited by 678
  5. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  6. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
  7. 2017Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equationscited by 373
  8. 2020B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Datacited by 335
  9. 2017PDE-Net: Learning PDEs from Datacited by 311
  10. 2018Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantificationcited by 199
  11. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 170
  12. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 161
20 more
  1. 2017Machine Learning of Linear Differential Equations using Gaussian Processescited by 140
  2. 2019Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networkscited by 129
  3. 2020Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networkscited by 123
  4. 2018A high-bias, low-variance introduction to Machine Learning for physicistscited by 108
  5. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating a class of inverse problems for PDEscited by 102
  6. 2022Physics-Informed Machine Learning: A Survey on Problems, Methods and Applicationscited by 92
  7. 2021Physics-based Deep Learningcited by 68
  8. 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 65
  9. 2020NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation frameworkcited by 58
  10. 2020DPM: A Novel Training Method for Physics-Informed Neural Networks in Extrapolationcited by 45
  11. 2016Inferring solutions of differential equations using noisy multi-fidelity datacited by 38
  12. 2020Physics Informed Neural Networks for Simulating Radiative Transfercited by 35
  13. 2022Adaptive Self-supervision Algorithms for Physics-informed Neural Networkscited by 24
  14. 2022Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computingcited by 24
  15. 2022Bayesian Learning for Neural Networks: an algorithmic surveycited by 23
  16. 2022Constraining Gaussian Processes to Systems of Linear Ordinary Differential Equationscited by 14
  17. 2020Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learningcited by 12
  18. 2021Bayesian Deep Learning for Partial Differential Equation Parameter Discovery with Sparse and Noisy Datacited by 12
  19. 2020CoPhy-PGNN: Learning Physics-guided Neural Networks with Competing Loss Functions for Solving Eigenvalue Problemscited by 11
  20. 2023A Bayesian Framework for learning governing Partial Differential Equation from Datacited by 8

Built on by

Not cited yet.