Enhanced physics-informed neural networks with Augmented Lagrangian relaxation method (AL-PINNs)

Cited 7 time in webofscience Cited 0 time in scopus
  • Hit : 110
  • Download : 0
Physics-Informed Neural Networks (PINNs) have become a prominent application of deep learning in sci-entific computation, as they are powerful approximators of solutions to nonlinear partial differential equations (PDEs). There have been numerous attempts to facilitate the training process of PINNs by adjusting the weight of each component of the loss function, called adaptive loss-balancing algorithms. In this paper, we propose an Augmented Lagrangian relaxation method for PINNs (AL-PINNs). We treat the initial and boundary conditions as constraints for the optimization problem of the PDE residual. By employing Augmented Lagrangian relaxation, the constrained optimization problem becomes a sequen-tial max-min problem so that the learnable parameters k adaptively balance each loss component. Our theoretical analysis reveals that the sequence of minimizers of the proposed loss functions converges to an actual solution for the Helmholtz, viscous Burgers, and Klein-Gordon equations. We demonstrate through various numerical experiments that AL-PINNs yield a much smaller relative error compared with that of state-of-the-art adaptive loss-balancing algorithms.& COPY; 2023 Elsevier B.V. All rights reserved.
Publisher
ELSEVIER
Issue Date
2023-09
Language
English
Article Type
Article
Citation

NEUROCOMPUTING, v.548

ISSN
0925-2312
DOI
10.1016/j.neucom.2023.126424
URI
http://hdl.handle.net/10203/310834
Appears in Collection
RIMS Journal Papers
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0