Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions

Abstract In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial differential equations without incurring the curse of dimension. However, all this work has been restricted to problems formulated on the whol...

Full description

Saved in:
Bibliographic Details
Published inIMA journal of numerical analysis Vol. 42; no. 3; pp. 2055 - 2082
Main Authors Grohs, Philipp, Herrmann, Lukas
Format Journal Article
LanguageEnglish
Published Oxford University Press 22.07.2022
Subjects
Online AccessGet full text
ISSN0272-4979
1464-3642
DOI10.1093/imanum/drab031

Cover

Abstract Abstract In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial differential equations without incurring the curse of dimension. However, all this work has been restricted to problems formulated on the whole Euclidean domain. On the other hand, most problems in engineering and in the sciences are formulated on finite domains and subjected to boundary conditions. The present paper considers an important such model problem, namely the Poisson equation on a domain $D\subset \mathbb {R}^d$ subject to Dirichlet boundary conditions. It is shown that DNNs are capable of representing solutions of that problem without incurring the curse of dimension. The proofs are based on a probabilistic representation of the solution to the Poisson equation as well as a suitable sampling method.
AbstractList Abstract In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial differential equations without incurring the curse of dimension. However, all this work has been restricted to problems formulated on the whole Euclidean domain. On the other hand, most problems in engineering and in the sciences are formulated on finite domains and subjected to boundary conditions. The present paper considers an important such model problem, namely the Poisson equation on a domain $D\subset \mathbb {R}^d$ subject to Dirichlet boundary conditions. It is shown that DNNs are capable of representing solutions of that problem without incurring the curse of dimension. The proofs are based on a probabilistic representation of the solution to the Poisson equation as well as a suitable sampling method.
In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial differential equations without incurring the curse of dimension. However, all this work has been restricted to problems formulated on the whole Euclidean domain. On the other hand, most problems in engineering and in the sciences are formulated on finite domains and subjected to boundary conditions. The present paper considers an important such model problem, namely the Poisson equation on a domain $D\subset \mathbb {R}^d$ subject to Dirichlet boundary conditions. It is shown that DNNs are capable of representing solutions of that problem without incurring the curse of dimension. The proofs are based on a probabilistic representation of the solution to the Poisson equation as well as a suitable sampling method.
Author Herrmann, Lukas
Grohs, Philipp
Author_xml – sequence: 1
  givenname: Philipp
  surname: Grohs
  fullname: Grohs, Philipp
– sequence: 2
  givenname: Lukas
  surname: Herrmann
  fullname: Herrmann, Lukas
  email: lukas.herrmann@ricam.oeaw.ac.at
BookMark eNqFkE1LAzEYhINUsK1ePefqYdt8NWmO0tYPKOhBj7Jks1kb3SZLkqX235vangTx8DLwMs8wzAgMnHcGgGuMJhhJOrVb5frttA6qQhSfgSFmnBWUMzIAQ0QEKZgU8gKMYvxACDEu0BC8LY3poDN9UG2WtPPhE6quC_4r5yXrHWx8gBv7vilquzUu5le2mra1XbIaPi9XEe5s2sDK965WYQ-1d7U9oPESnDeqjebqpGPwerd6WTwU66f7x8XtutBE0FTgGVaGYsIqTXVj5vnkHAsuFaFGz2rVNIiRWjOKhay41FJTrpUSak41l4iOATvm6uBjDKYptU0_7VNQti0xKg8TlceJytNEGZv8wrqQLWH_N3BzBHzf_ef9BmNhf8U
CitedBy_id crossref_primary_10_1109_ACCESS_2023_3343249
crossref_primary_10_3390_math12091407
crossref_primary_10_4213_sm9791
crossref_primary_10_4213_sm9791e
crossref_primary_10_1007_s10543_025_01058_9
crossref_primary_10_1016_j_matcom_2024_01_019
crossref_primary_10_3390_risks8040136
crossref_primary_10_1137_21M1465718
crossref_primary_10_1063_5_0226232
crossref_primary_10_1063_5_0159224
crossref_primary_10_1007_s00365_021_09541_6
crossref_primary_10_1016_j_jco_2023_101779
Cites_doi 10.1109/TIT.2021.3062161
10.1088/1361-6420/abaf64
10.1093/imanum/drx042
10.1006/jcom.1999.0499
10.1214/aoms/1177728169
10.1016/j.jcp.2020.109409
10.1007/BF01831723
10.1090/S0002-9947-1961-0137148-5
10.1093/comjnl/1.3.142
10.1007/s40304-018-0127-z
10.1016/j.neucom.2018.06.003
10.1016/j.neunet.2017.07.002
10.1080/03605301003657843
10.1142/S0219530519410136
10.1016/j.jcp.2020.109792
10.1137/19M125649X
10.1016/j.jcp.2016.03.005
10.1007/BF03014033
10.1007/978-3-642-12245-3
10.1016/j.jcp.2020.109339
10.1137/100787842
10.1007/s10915-018-00903-0
10.1214/aop/1176994833
10.1007/s10208-015-9265-9
10.1016/j.jcp.2018.08.029
10.1007/978-1-4684-0302-2
10.1051/m2an:2004005
10.2478/cmam-2011-0020
10.1142/S0219530518500203
10.1137/18M118709X
10.1007/s00365-009-9064-0
ContentType Journal Article
Copyright The Author(s) 2021. Published by Oxford University Press on behalf of the Institute of Mathematics and its Applications. All rights reserved. 2021
Copyright_xml – notice: The Author(s) 2021. Published by Oxford University Press on behalf of the Institute of Mathematics and its Applications. All rights reserved. 2021
DBID AAYXX
CITATION
DOI 10.1093/imanum/drab031
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Mathematics
EISSN 1464-3642
EndPage 2082
ExternalDocumentID 10_1093_imanum_drab031
10.1093/imanum/drab031
GroupedDBID -E4
-~X
.2P
.DC
.I3
0R~
18M
1TH
29I
4.4
482
48X
5GY
5VS
5WA
6OB
6TJ
70D
8WZ
A6W
AAIJN
AAJKP
AAJQQ
AAMVS
AAOGV
AAPQZ
AAPXW
AARHZ
AAUAY
AAUQX
AAVAP
AAWDT
ABAZT
ABDFA
ABDTM
ABEFU
ABEJV
ABEUO
ABGNP
ABIME
ABIXL
ABJNI
ABLJU
ABNGD
ABNKS
ABPIB
ABPQP
ABPTD
ABQLI
ABQTQ
ABSMQ
ABTAH
ABVGC
ABWST
ABXVV
ABZBJ
ABZEO
ACFRR
ACGFO
ACGFS
ACGOD
ACIWK
ACPQN
ACUFI
ACUKT
ACUTJ
ACUXJ
ACVCV
ACYTK
ACZBC
ADEYI
ADEZT
ADGZP
ADHKW
ADHZD
ADIPN
ADNBA
ADOCK
ADQBN
ADRDM
ADRTK
ADVEK
ADYVW
ADZXQ
AECKG
AEGPL
AEGXH
AEHUL
AEJOX
AEKKA
AEKPW
AEKSI
AEMDU
AENEX
AENZO
AEPUE
AETBJ
AEWNT
AFFNX
AFFZL
AFIYH
AFOFC
AFSHK
AFYAG
AGINJ
AGKEF
AGKRT
AGMDO
AGQXC
AGSYK
AHXPO
AI.
AIAGR
AIJHB
AJDVS
AJEEA
AJEUX
AJNCP
ALMA_UNASSIGNED_HOLDINGS
ALTZX
ALUQC
ALXQX
ANAKG
ANFBD
APIBT
APJGH
APWMN
AQDSO
ASAOO
ASPBG
ATDFG
ATGXG
ATTQO
AVWKF
AXUDD
AZFZN
AZVOD
BAYMD
BCRHZ
BEFXN
BEYMZ
BFFAM
BGNUA
BHONS
BKEBE
BPEOZ
BQUQU
BTQHN
CAG
CDBKE
COF
CS3
CXTWN
CZ4
DAKXR
DFGAJ
DILTD
DU5
D~K
EBS
EE~
EJD
ELUNK
F9B
FEDTE
FLIZI
FLUFQ
FOEOM
FQBLK
GAUVT
GJXCC
H13
H5~
HAR
HVGLF
HW0
HZ~
IOX
J21
JAVBF
JXSIZ
KAQDR
KBUDW
KOP
KSI
KSN
M-Z
M49
MBTAY
N9A
NGC
NMDNZ
NOMLY
NU-
NVLIB
O0~
O9-
OCL
ODMLO
OJQWA
OJZSN
OWPYF
O~Y
P2P
PAFKI
PB-
PEELM
PQQKQ
Q1.
Q5Y
QBD
R44
RD5
RIG
RNI
ROL
ROX
ROZ
RUSNO
RW1
RXO
RZF
RZO
T9H
TCN
TJP
UPT
VH1
WH7
X7H
XOL
YAYTL
YKOAZ
YXANX
ZKX
ZY4
~91
AAYXX
ADYJX
AHGBF
AJBYB
AMVHM
CITATION
ID FETCH-LOGICAL-c273t-151ae3124bc3cfe8cfe981769a23ec5daff042dc43179b69c9c36caa7a83c6903
ISSN 0272-4979
IngestDate Thu Apr 24 22:50:29 EDT 2025
Wed Oct 01 03:30:23 EDT 2025
Wed Apr 02 07:03:48 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords neural network approximation
Monte Carlo methods
high-dimensional approximation
Language English
License This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model)
https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c273t-151ae3124bc3cfe8cfe981769a23ec5daff042dc43179b69c9c36caa7a83c6903
PageCount 28
ParticipantIDs crossref_citationtrail_10_1093_imanum_drab031
crossref_primary_10_1093_imanum_drab031
oup_primary_10_1093_imanum_drab031
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2022-07-22
PublicationDateYYYYMMDD 2022-07-22
PublicationDate_xml – month: 07
  year: 2022
  text: 2022-07-22
  day: 22
PublicationDecade 2020
PublicationTitle IMA journal of numerical analysis
PublicationYear 2022
Publisher Oxford University Press
Publisher_xml – name: Oxford University Press
References Gazzola (2022071909084174000_ref13) 2010
Herrmann (2022071909084174000_ref23) 2020; 36
Han (2022071909084174000_ref22) 2020; 423
Wang (2022071909084174000_ref44) 2016; 314
Kutyniok (2022071909084174000_ref27) 2019
Port (2022071909084174000_ref38) 1978
Gower (2022071909084174000_ref18) 1958; 1
Kyprianou (2022071909084174000_ref28) 2018; 38
Gilbarg (2022071909084174000_ref16) 1983
Jentzen (2022071909084174000_ref24) 2018
Karatzas (2022071909084174000_ref25) 1988
Schilling (2022071909084174000_ref39) 2014
Yarotsky (2022071909084174000_ref46) 2017; 94
Zang (2022071909084174000_ref47) 2020; 411
Geist (2022071909084174000_ref14) 2020
Oksendal (2022071909084174000_ref35) 1998
Wendel (2022071909084174000_ref45) 1980; 8
Schwab (2022071909084174000_ref40) 2019; 17
Grohs (2022071909084174000_ref20) 2018
Gonon (2022071909084174000_ref17) 2019
Mörters (2022071909084174000_ref32) 2010
Lye (2022071909084174000_ref29) 2020; 410
Beck (2022071909084174000_ref1) 2020
Motoo (2022071909084174000_ref33) 1959; 11
Shen (2022071909084174000_ref41) 2010; 32
Grohs (2022071909084174000_ref19) 2021
Muller (2022071909084174000_ref34) 1956; 27
Opschoor (2022071909084174000_ref37) 2021
Bölcskei (2022071909084174000_ref4) 2019; 1
Bungartz (2022071909084174000_ref5) 1999; 15
Getoor (2022071909084174000_ref15) 1961; 101
McCane (2022071909084174000_ref30) 2018; 313
Boggio (2022071909084174000_ref3) 1905; 20
Cianchi (2022071909084174000_ref6) 2011; 36
Grohs (2022071909084174000_ref21) 2019
Weinan (2022071909084174000_ref10) 2018; 6
Elbrächter (2022071909084174000_ref11) 2018
Kressner (2022071909084174000_ref26) 2011; 11
Weinan (2022071909084174000_ref9) 2019; 79
von Petersdorff (2022071909084174000_ref43) 2004; 38
Opschoor (2022071909084174000_ref36) 2020; 18
Elbrächter (2022071909084174000_ref12) 2021; 67
Berner (2022071909084174000_ref2) 2020; 2
Dijkema (2022071909084174000_ref8) 2009; 30
Dahmen (2022071909084174000_ref7) 2016; 16
Mishra (2022071909084174000_ref31) 2020
Sirignano (2022071909084174000_ref42) 2018; 375
References_xml – volume: 67
  start-page: 2581
  year: 2021
  ident: 2022071909084174000_ref12
  article-title: Deep neural network approximation theory
  publication-title: IEEE Trans. Inform. Theory
  doi: 10.1109/TIT.2021.3062161
– volume: 36
  start-page: 125011
  year: 2020
  ident: 2022071909084174000_ref23
  article-title: Deep neural network expression of posterior expectations in Bayesian PDE inversion
  publication-title: Inverse Problems
  doi: 10.1088/1361-6420/abaf64
– volume-title: Technical Report 2018-34 Seminar for Applied Mathematics
  year: 2018
  ident: 2022071909084174000_ref24
  article-title: A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
– volume: 38
  start-page: 1550
  year: 2018
  ident: 2022071909084174000_ref28
  article-title: Unbiased ‘walk-on-spheres’ Monte Carlo methods for the fractional Laplacian
  publication-title: IMA J. Numer. Anal.
  doi: 10.1093/imanum/drx042
– volume-title: Technical Report 2020-31 Seminar for Applied Mathematics
  year: 2020
  ident: 2022071909084174000_ref31
  article-title: Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences
– volume: 15
  start-page: 167
  year: 1999
  ident: 2022071909084174000_ref5
  article-title: A note on the complexity of solving Poisson’s equation for spaces of bounded mixed derivatives
  publication-title: J. Complexity
  doi: 10.1006/jcom.1999.0499
– year: 2021
  ident: 2022071909084174000_ref19
  article-title: Deep neural network approximation for high-dimensional parabolic Hamilton–Jacobi–Bellman equations
– volume: 27
  start-page: 569
  year: 1956
  ident: 2022071909084174000_ref34
  article-title: Some continuous Monte Carlo methods for the Dirichlet problem
  publication-title: Ann. Math. Statist.
  doi: 10.1214/aoms/1177728169
– volume: 411
  start-page: 14
  year: 2020
  ident: 2022071909084174000_ref47
  article-title: Weak adversarial networks for high-dimensional partial differential equations
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2020.109409
– year: 2019
  ident: 2022071909084174000_ref27
  article-title: A theoretical analysis of deep neural networks and parametric PDEs
– volume-title: Brownian Motion
  year: 2010
  ident: 2022071909084174000_ref32
  article-title: Cambridge Series in Statistical and Probabilistic Mathematics
– volume-title: Brownian Motion and Classical Potential Theory
  year: 1978
  ident: 2022071909084174000_ref38
  article-title: Probability and Mathematical Statistics
– volume: 11
  start-page: 49
  year: 1959
  ident: 2022071909084174000_ref33
  article-title: Some evaluations for continuous Monte Carlo method by using Brownian hitting process
  publication-title: Ann. Inst. Statist. Math.
  doi: 10.1007/BF01831723
– volume: 101
  start-page: 75
  year: 1961
  ident: 2022071909084174000_ref15
  article-title: First passage times for symmetric stable processes in space
  publication-title: Trans. Amer. Math. Soc.
  doi: 10.1090/S0002-9947-1961-0137148-5
– volume: 1
  start-page: 142
  year: 1958
  ident: 2022071909084174000_ref18
  article-title: A note on an iterative method for root extraction
  publication-title: Comput. J.
  doi: 10.1093/comjnl/1.3.142
– year: 2018
  ident: 2022071909084174000_ref20
  article-title: A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black–Scholes partial differential equations
  publication-title: Mem. Amer. Math. Soc.
– volume: 6
  start-page: 1
  year: 2018
  ident: 2022071909084174000_ref10
  article-title: The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
  publication-title: Commun. Math. Stat.
  doi: 10.1007/s40304-018-0127-z
– volume-title: Elliptic Partial Differential Equations of Second Order
  year: 1983
  ident: 2022071909084174000_ref16
  article-title: Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences]
– volume-title: Technical Report 2019-61 Seminar for Applied Mathematics
  year: 2019
  ident: 2022071909084174000_ref17
  article-title: Uniform error estimates for artificial neural network approximations for heat equations
– volume: 313
  start-page: 119
  year: 2018
  ident: 2022071909084174000_ref30
  article-title: Efficiency of deep networks for radially symmetric functions
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.06.003
– volume: 94
  start-page: 103
  year: 2017
  ident: 2022071909084174000_ref46
  article-title: Error bounds for approximations with deep ReLU networks
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2017.07.002
– volume: 36
  start-page: 100
  year: 2011
  ident: 2022071909084174000_ref6
  article-title: Global Lipschitz regularity for a class of quasilinear elliptic equations
  publication-title: Comm. Partial Differential Equations
  doi: 10.1080/03605301003657843
– year: 2018
  ident: 2022071909084174000_ref11
  article-title: DNN expression rate analysis of high-dimensional PDEs: application to option pricing
  publication-title: Constr. Approx.
– volume: 18
  start-page: 715
  year: 2020
  ident: 2022071909084174000_ref36
  article-title: Deep ReLU networks and high-order finite element methods
  publication-title: Anal. Appl. (Singap.)
  doi: 10.1142/S0219530519410136
– volume: 423
  start-page: 13
  year: 2020
  ident: 2022071909084174000_ref22
  article-title: Solving high-dimensional eigenvalue problems using deep neural networks: a diffusion Monte Carlo like approach
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2020.109792
– volume: 2
  start-page: 631
  year: 2020
  ident: 2022071909084174000_ref2
  article-title: Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black–Scholes partial differential equations
  publication-title: SIAM J. Math. Data Sci.
  doi: 10.1137/19M125649X
– volume-title: Constr. Approx
  year: 2021
  ident: 2022071909084174000_ref37
  article-title: Exponential ReLU DNN expression of holomorphic maps in high dimension
– volume: 314
  start-page: 244
  year: 2016
  ident: 2022071909084174000_ref44
  article-title: Sparse grid discontinuous Galerkin methods for high-dimensional elliptic equations
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2016.03.005
– volume-title: Technical Report 2002-16 Seminar for Applied Mathematics
  year: 2020
  ident: 2022071909084174000_ref1
  article-title: Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
– volume: 20
  start-page: 97
  year: 1905
  ident: 2022071909084174000_ref3
  article-title: Sulle funzioni di green d’ordinem
  publication-title: Rend. Circ. Mat. Palermo (2)
  doi: 10.1007/BF03014033
– volume-title: Polyharmonic Boundary Value Problems: Positivity Preserving and Nonlinear Higher Order Elliptic Equations in Bounded Domains
  year: 2010
  ident: 2022071909084174000_ref13
  article-title: Lecture Notes in Mathematics
  doi: 10.1007/978-3-642-12245-3
– volume: 410
  start-page: 26
  year: 2020
  ident: 2022071909084174000_ref29
  article-title: Deep learning observables in computational fluid dynamics
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2020.109339
– volume-title: Brownian Motion: An Introduction to Stochastic Processes
  year: 2014
  ident: 2022071909084174000_ref39
  article-title: De Gruyter Graduate
– volume: 32
  start-page: 3228
  year: 2010
  ident: 2022071909084174000_ref41
  article-title: Efficient spectral sparse grid methods and applications to high-dimensional elliptic problems
  publication-title: SIAM J. Sci. Comput.
  doi: 10.1137/100787842
– volume: 79
  start-page: 1534
  year: 2019
  ident: 2022071909084174000_ref9
  article-title: On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
  publication-title: J. Sci. Comput.
  doi: 10.1007/s10915-018-00903-0
– year: 2020
  ident: 2022071909084174000_ref14
  article-title: Numerical solution of the parametric diffusion equation by deep neural networks
– volume: 8
  start-page: 164
  year: 1980
  ident: 2022071909084174000_ref45
  article-title: Hitting spheres with Brownian motion
  publication-title: Ann. Probab.
  doi: 10.1214/aop/1176994833
– volume: 16
  start-page: 813
  year: 2016
  ident: 2022071909084174000_ref7
  article-title: Tensor-sparsity of solutions to high-dimensional elliptic partial differential equations
  publication-title: Found. Comput. Math.
  doi: 10.1007/s10208-015-9265-9
– volume: 375
  start-page: 1339
  year: 2018
  ident: 2022071909084174000_ref42
  article-title: DGM: a deep learning algorithm for solving partial differential equations
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2018.08.029
– volume-title: Brownian Motion and Stochastic Calculus
  year: 1988
  ident: 2022071909084174000_ref25
  article-title: Graduate Texts in Mathematics
  doi: 10.1007/978-1-4684-0302-2
– volume: 38
  start-page: 93
  year: 2004
  ident: 2022071909084174000_ref43
  article-title: Numerical solution of parabolic equations in high dimensions
  publication-title: ESAIM Math. Model. Numer. Anal.
  doi: 10.1051/m2an:2004005
– volume-title: Stochastic Differential Equations: An Introduction with Applications
  year: 1998
  ident: 2022071909084174000_ref35
  article-title: Universitext
– volume: 11
  start-page: 363
  year: 2011
  ident: 2022071909084174000_ref26
  article-title: Preconditioned low-rank methods for high-dimensional elliptic PDE eigenvalue problems
  publication-title: Comput. Methods Appl. Math.
  doi: 10.2478/cmam-2011-0020
– volume: 17
  start-page: 19
  year: 2019
  ident: 2022071909084174000_ref40
  article-title: Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
  publication-title: Anal. Appl. (Singap.)
  doi: 10.1142/S0219530518500203
– volume-title: Technical Report 2019-50 Seminar for Applied Mathematics
  year: 2019
  ident: 2022071909084174000_ref21
  article-title: Deep neural network approximations for Monte Carlo algorithms
– volume: 1
  start-page: 8
  year: 2019
  ident: 2022071909084174000_ref4
  article-title: Optimal approximation with sparsely connected deep neural networks
  publication-title: SIAM J. Math. Data Sci.
  doi: 10.1137/18M118709X
– volume: 30
  start-page: 423
  year: 2009
  ident: 2022071909084174000_ref8
  article-title: An adaptive wavelet method for solving high-dimensional elliptic PDEs
  publication-title: Constr. Approx.
  doi: 10.1007/s00365-009-9064-0
SSID ssj0004670
Score 2.48244
Snippet Abstract In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial...
In recent work it has been established that deep neural networks (DNNs) are capable of approximating solutions to a large class of parabolic partial...
SourceID crossref
oup
SourceType Enrichment Source
Index Database
Publisher
StartPage 2055
Title Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions
Volume 42
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Mathematics Source
  customDbUrl:
  eissn: 1464-3642
  dateEnd: 20241103
  omitProxy: false
  ssIdentifier: ssj0004670
  issn: 0272-4979
  databaseCode: AMVHM
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/mathematics-source
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS9xAEF_a86U-2Na2VNvKUgo-yGqym2wuj0dVroWUPqj4Isd-BUUbj_uA1r_e2Zu9fKil2oeEEDYD2fkxOzs78xtCvmSlilUqSxbZKGWJSR3rG6WZyoW1EXeKL8rHih9yeJx8P01Pm4D-orpkpnfNzYN1Jf-jVXgHevVVsk_QbC0UXsAz6BfuoGG4P0rH-86NdzwjJcxzhfncSBL---JXk0ToGYmZ9Sz-yMCx4zk4x56o9ef-Qahu04vuSpM_PgvdXjRBvOC2fisGbY6Jao7nPJ5mADlNmjSe6_NpE6gZN6HWia9OwDqH-aXqRBv4IjOVtwOQPOO-Kx2aOYdGM5EJEzLpWNWEt9Aj2iYyQl7esNzyCJsP3TPlSHMF01X5hs-HdqJ0FBaMDmv2ndWszjHE03UxQgmj8P1zssLB_kc9sjIoToZFq4Y2w3hc-L-a4FPsoYS9IKHjwPiiyJY_cvSKrIWNBB0gKl6TZ65aJy_DpoIGkz1dJ6tFTcw7fUPOPGQoQoYGyNAOZChAht6FDF1ChnrIUA8ZuoQMbSDzlhwfHhx9HbLQYYMZcFtnDNw95QS4eNoIU7o-XHk_zmSuuHAmtaoswahb473MXMvc5EZIo1Sm-sLIPBLvSK-6rtx7Qo0WqXDaSmvTBHYBysTgvFsrTSljHWcbhC2nbWQC_bzvgnI1elhRG2S7Hj9G4pW_jvwMWvjHoM1Hi_tAXjTA_0h6s8ncfQLHc6a3AmZuARSjjvo
linkProvider EBSCOhost
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=Deep+neural+network+approximation+for+high-dimensional+elliptic+PDEs+with+boundary+conditions&rft.jtitle=IMA+journal+of+numerical+analysis&rft.au=Grohs%2C+Philipp&rft.au=Herrmann%2C+Lukas&rft.date=2022-07-22&rft.issn=0272-4979&rft.eissn=1464-3642&rft.volume=42&rft.issue=3&rft.spage=2055&rft.epage=2082&rft_id=info:doi/10.1093%2Fimanum%2Fdrab031&rft.externalDBID=n%2Fa&rft.externalDocID=10_1093_imanum_drab031
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0272-4979&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0272-4979&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0272-4979&client=summon