Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations
Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep learning methods have been recently developed to t...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
10.05.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep learning methods have been recently developed to try and solve high-dimensional PDEs by approximating the solution using a neural network. In this paper, we prove global convergence for one of the commonly-used deep learning algorithms for solving PDEs, the Deep Galerkin Method (DGM). DGM trains a neural network approximator to solve the PDE using stochastic gradient descent. We prove that, as the number of hidden units in the single-layer network goes to infinity (i.e., in the ``wide network limit"), the trained neural network converges to the solution of an infinite-dimensional linear ordinary differential equation (ODE). The PDE residual of the limiting approximator converges to zero as the training time \(\rightarrow \infty\). Under mild assumptions, this convergence also implies that the neural network approximator converges to the solution of the PDE. A closely related class of deep learning methods for PDEs is Physics Informed Neural Networks (PINNs). Using the same mathematical techniques, we can prove a similar global convergence result for the PINN neural network approximators. Both proofs require analyzing a kernel function in the limit ODE governing the evolution of the limit neural network approximator. A key technical challenge is that the kernel function, which is a composition of the PDE operator and the neural tangent kernel (NTK) operator, lacks a spectral gap, therefore requiring a careful analysis of its properties. |
---|---|
AbstractList | Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep learning methods have been recently developed to try and solve high-dimensional PDEs by approximating the solution using a neural network. In this paper, we prove global convergence for one of the commonly-used deep learning algorithms for solving PDEs, the Deep Galerkin Method (DGM). DGM trains a neural network approximator to solve the PDE using stochastic gradient descent. We prove that, as the number of hidden units in the single-layer network goes to infinity (i.e., in the ``wide network limit"), the trained neural network converges to the solution of an infinite-dimensional linear ordinary differential equation (ODE). The PDE residual of the limiting approximator converges to zero as the training time \(\rightarrow \infty\). Under mild assumptions, this convergence also implies that the neural network approximator converges to the solution of the PDE. A closely related class of deep learning methods for PDEs is Physics Informed Neural Networks (PINNs). Using the same mathematical techniques, we can prove a similar global convergence result for the PINN neural network approximators. Both proofs require analyzing a kernel function in the limit ODE governing the evolution of the limit neural network approximator. A key technical challenge is that the kernel function, which is a composition of the PDE operator and the neural tangent kernel (NTK) operator, lacks a spectral gap, therefore requiring a careful analysis of its properties. |
Author | Jiang, Deqing Sirignano, Justin Cohen, Samuel N |
Author_xml | – sequence: 1 givenname: Deqing surname: Jiang fullname: Jiang, Deqing – sequence: 2 givenname: Justin surname: Sirignano fullname: Sirignano, Justin – sequence: 3 givenname: Samuel surname: Cohen middlename: N fullname: Cohen, Samuel N |
BookMark | eNqNjMsKwjAQRYMo-PyHAddCm1bbfetroRR0X6NONDXM2KT1-xXxA1xdDudwh6JLTNgRAxlF4SyNpeyLifdVEARykcj5PBqI09ryWVnImF7obkgXBNaQIz5hrSy6hyFQdIViu9972GFz56sHzQ4ObF-GblAo15jPRW60Rof0hWXdqsYw-bHoaWU9Tn47EtPV8phtZk_HdYu-KStuHX1UKdNQyjhOwyT6r3oD6LBF3A |
ContentType | Paper |
Copyright | 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Databases Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28122448173 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 15:42:00 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28122448173 |
OpenAccessLink | https://www.proquest.com/docview/2812244817?pq-origsite=%requestingapplication% |
PQID | 2812244817 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2812244817 |
PublicationCentury | 2000 |
PublicationDate | 20230510 |
PublicationDateYYYYMMDD | 2023-05-10 |
PublicationDate_xml | – month: 05 year: 2023 text: 20230510 day: 10 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.4748828 |
SecondaryResourceType | preprint |
Snippet | Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Convergence Deep learning Finite difference method Galerkin method Kernel functions Machine learning Mathematical analysis Neural networks Operators (mathematics) Ordinary differential equations Partial differential equations Teaching methods |
Title | Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations |
URI | https://www.proquest.com/docview/2812244817 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3JasMwEB3amEJvXemSBkF7Fa33-FRoYicUbEwXyC21tZxK7ETptd_eGcVpD4UchUBYtvxG8zR6D-DuwZU6iauQa-kpjoCHv1QgfZ7UISmhyihUlCjmRTR9D55n4awj3ExXVrnFRAvUshHEkd97QzoDCoZu_NguOblG0elqZ6GxD45LSnh0Uzyb_HIsXhTjjtn_B7M2dmRH4JRVq1bHsKcWJ3BgSy6FOYWPjdw-G1Hdt70CqVij2Viplk0QtonEZpjnM0y8C8Nya_VsGG4y2WvzSTwAK-m74xDjzuXENtLlRr3bnMFtlr6Npnz7WPNu4Zj53zT9c-gtmoW6ACZq4n4wjmglAqnD2vcwERF-LKI40V51Cf1dI13t7r6GQ_JQ51aStA-99epL3WCkXdcD-zoH4DylRfmCrfw7_QFuhojq |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3JTsMwEB1BKwQ3VrEUsARXCxpnPXFomwZookoUqbeQeDlVSVqX_8fjpnBA6tGyZHl943kezwN4fO4LFQWFR5VwJDWAZ46UKxiNSg8zoQrfk-goppmffLpvc2_eEm66DavcYqIFalFz5MifnBDfgNywH7w0S4qqUfi62kpo7EPXZT7DfR7G41-OxfEDc2Nm_2DW2o74GLrTopGrE9iT1Skc2JBLrs_ga5Nunwww7tt-gZSkVmQoZUPGBraRxCbGzyfG8c40Sa3Usybmkkk-6gXyAGSK626aGLYqJ7YwWm6yd-tzeIhHs0FCt93K242j879hsgvoVHUlL4HwErkfY0eU5K5QXskc44hwFnA_iJRTXEFvV0vXu6vv4TCZpZN88pq938AR6qlTm560B5316lveGqu7Lu_s1P4Ab7qJBw |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Global+Convergence+of+Deep+Galerkin+and+PINNs+Methods+for+Solving+Partial+Differential+Equations&rft.jtitle=arXiv.org&rft.au=Jiang%2C+Deqing&rft.au=Sirignano%2C+Justin&rft.au=Cohen%2C+Samuel+N&rft.date=2023-05-10&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |