Neural Approximate Inverse Preconditioners Article Swipe
Tianshi Xu
,
Ruipeng Li
,
Yuanzhe Xi
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2510.13034
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2510.13034
In this paper, we propose a data-driven framework for constructing efficient approximate inverse preconditioners for elliptic partial differential equations (PDEs) by learning the Green's function of the underlying operator with neural networks (NNs). The training process integrates four key components: an adaptive multiscale neural architecture ($α$MSNN) that captures hierarchical features across near-, middle-, and far-field regimes; the use of coarse-grid anchor data to ensure physical identifiability; a multi-$\varepsilon$ staged training protocol that progressively refines the Green's function representation across spatial scales; and an overlapping domain decomposition that enables local adaptation while maintaining global consistency. Once trained, the NN-approximated Green's function is directly compressed into either a hierarchical ($\mathcal{H}$-) matrix or a sparse matrix-using only the mesh geometry and the network output. This geometric construction achieves nearly linear complexity in both setup and application while preserving the spectral properties essential for effective preconditioning. Numerical experiments on challenging elliptic PDEs demonstrate that the resulting preconditioners consistently yield fast convergence and small iteration counts.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2510.13034
- https://arxiv.org/pdf/2510.13034
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415274434
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415274434Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2510.13034Digital Object Identifier
- Title
-
Neural Approximate Inverse PreconditionersWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-14Full publication date if available
- Authors
-
Tianshi Xu, Ruipeng Li, Yuanzhe XiList of authors in order
- Landing page
-
https://arxiv.org/abs/2510.13034Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2510.13034Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2510.13034Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415274434 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2510.13034 |
| ids.doi | https://doi.org/10.48550/arxiv.2510.13034 |
| ids.openalex | https://openalex.org/W4415274434 |
| fwci | |
| type | preprint |
| title | Neural Approximate Inverse Preconditioners |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11206 |
| topics[0].field.id | https://openalex.org/fields/31 |
| topics[0].field.display_name | Physics and Astronomy |
| topics[0].score | 0.9771000146865845 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3109 |
| topics[0].subfield.display_name | Statistical and Nonlinear Physics |
| topics[0].display_name | Model Reduction and Neural Networks |
| topics[1].id | https://openalex.org/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9585000276565552 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Neural Networks and Applications |
| topics[2].id | https://openalex.org/T11034 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9053999781608582 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1711 |
| topics[2].subfield.display_name | Signal Processing |
| topics[2].display_name | Digital Filter Design and Implementation |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2510.13034 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2510.13034 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2510.13034 |
| locations[1].id | doi:10.48550/arxiv.2510.13034 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2510.13034 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100949672 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Tianshi Xu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xu, Tianshi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101509235 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2802-5763 |
| authorships[1].author.display_name | Ruipeng Li |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Rui Peng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5056635728 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0361-0931 |
| authorships[2].author.display_name | Yuanzhe Xi |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Xi, Yuanzhe |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2510.13034 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-17T00:00:00 |
| display_name | Neural Approximate Inverse Preconditioners |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11206 |
| primary_topic.field.id | https://openalex.org/fields/31 |
| primary_topic.field.display_name | Physics and Astronomy |
| primary_topic.score | 0.9771000146865845 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3109 |
| primary_topic.subfield.display_name | Statistical and Nonlinear Physics |
| primary_topic.display_name | Model Reduction and Neural Networks |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2510.13034 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2510.13034 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2510.13034 |
| primary_location.id | pmh:oai:arXiv.org:2510.13034 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2510.13034 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2510.13034 |
| publication_date | 2025-10-14 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 5, 66, 105, 110 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.an | 40, 82 |
| abstract_inverted_index.by | 20 |
| abstract_inverted_index.in | 128 |
| abstract_inverted_index.is | 100 |
| abstract_inverted_index.of | 25, 58 |
| abstract_inverted_index.on | 144 |
| abstract_inverted_index.or | 109 |
| abstract_inverted_index.to | 62 |
| abstract_inverted_index.we | 3 |
| abstract_inverted_index.The | 33 |
| abstract_inverted_index.and | 53, 81, 117, 131, 157 |
| abstract_inverted_index.for | 8, 14, 139 |
| abstract_inverted_index.key | 38 |
| abstract_inverted_index.the | 22, 26, 56, 74, 96, 114, 118, 135, 150 |
| abstract_inverted_index.use | 57 |
| abstract_inverted_index.Once | 94 |
| abstract_inverted_index.PDEs | 147 |
| abstract_inverted_index.This | 121 |
| abstract_inverted_index.both | 129 |
| abstract_inverted_index.data | 61 |
| abstract_inverted_index.fast | 155 |
| abstract_inverted_index.four | 37 |
| abstract_inverted_index.into | 103 |
| abstract_inverted_index.mesh | 115 |
| abstract_inverted_index.only | 113 |
| abstract_inverted_index.that | 46, 71, 86, 149 |
| abstract_inverted_index.this | 1 |
| abstract_inverted_index.with | 29 |
| abstract_inverted_index.local | 88 |
| abstract_inverted_index.setup | 130 |
| abstract_inverted_index.small | 158 |
| abstract_inverted_index.while | 90, 133 |
| abstract_inverted_index.yield | 154 |
| abstract_inverted_index.(NNs). | 32 |
| abstract_inverted_index.(PDEs) | 19 |
| abstract_inverted_index.across | 50, 78 |
| abstract_inverted_index.anchor | 60 |
| abstract_inverted_index.domain | 84 |
| abstract_inverted_index.either | 104 |
| abstract_inverted_index.ensure | 63 |
| abstract_inverted_index.global | 92 |
| abstract_inverted_index.linear | 126 |
| abstract_inverted_index.matrix | 108 |
| abstract_inverted_index.near-, | 51 |
| abstract_inverted_index.nearly | 125 |
| abstract_inverted_index.neural | 30, 43 |
| abstract_inverted_index.paper, | 2 |
| abstract_inverted_index.sparse | 111 |
| abstract_inverted_index.staged | 68 |
| abstract_inverted_index.Green's | 23, 75, 98 |
| abstract_inverted_index.counts. | 160 |
| abstract_inverted_index.enables | 87 |
| abstract_inverted_index.inverse | 12 |
| abstract_inverted_index.network | 119 |
| abstract_inverted_index.output. | 120 |
| abstract_inverted_index.partial | 16 |
| abstract_inverted_index.process | 35 |
| abstract_inverted_index.propose | 4 |
| abstract_inverted_index.refines | 73 |
| abstract_inverted_index.scales; | 80 |
| abstract_inverted_index.spatial | 79 |
| abstract_inverted_index.achieves | 124 |
| abstract_inverted_index.adaptive | 41 |
| abstract_inverted_index.captures | 47 |
| abstract_inverted_index.directly | 101 |
| abstract_inverted_index.elliptic | 15, 146 |
| abstract_inverted_index.features | 49 |
| abstract_inverted_index.function | 24, 76, 99 |
| abstract_inverted_index.geometry | 116 |
| abstract_inverted_index.learning | 21 |
| abstract_inverted_index.middle-, | 52 |
| abstract_inverted_index.networks | 31 |
| abstract_inverted_index.operator | 28 |
| abstract_inverted_index.physical | 64 |
| abstract_inverted_index.protocol | 70 |
| abstract_inverted_index.regimes; | 55 |
| abstract_inverted_index.spectral | 136 |
| abstract_inverted_index.trained, | 95 |
| abstract_inverted_index.training | 34, 69 |
| abstract_inverted_index.Numerical | 142 |
| abstract_inverted_index.effective | 140 |
| abstract_inverted_index.efficient | 10 |
| abstract_inverted_index.equations | 18 |
| abstract_inverted_index.essential | 138 |
| abstract_inverted_index.far-field | 54 |
| abstract_inverted_index.framework | 7 |
| abstract_inverted_index.geometric | 122 |
| abstract_inverted_index.iteration | 159 |
| abstract_inverted_index.resulting | 151 |
| abstract_inverted_index.($α$MSNN) | 45 |
| abstract_inverted_index.adaptation | 89 |
| abstract_inverted_index.complexity | 127 |
| abstract_inverted_index.compressed | 102 |
| abstract_inverted_index.integrates | 36 |
| abstract_inverted_index.multiscale | 42 |
| abstract_inverted_index.preserving | 134 |
| abstract_inverted_index.properties | 137 |
| abstract_inverted_index.underlying | 27 |
| abstract_inverted_index.application | 132 |
| abstract_inverted_index.approximate | 11 |
| abstract_inverted_index.challenging | 145 |
| abstract_inverted_index.coarse-grid | 59 |
| abstract_inverted_index.components: | 39 |
| abstract_inverted_index.convergence | 156 |
| abstract_inverted_index.data-driven | 6 |
| abstract_inverted_index.demonstrate | 148 |
| abstract_inverted_index.experiments | 143 |
| abstract_inverted_index.maintaining | 91 |
| abstract_inverted_index.overlapping | 83 |
| abstract_inverted_index.architecture | 44 |
| abstract_inverted_index.consistency. | 93 |
| abstract_inverted_index.consistently | 153 |
| abstract_inverted_index.constructing | 9 |
| abstract_inverted_index.construction | 123 |
| abstract_inverted_index.differential | 17 |
| abstract_inverted_index.hierarchical | 48, 106 |
| abstract_inverted_index.matrix-using | 112 |
| abstract_inverted_index.decomposition | 85 |
| abstract_inverted_index.progressively | 72 |
| abstract_inverted_index.representation | 77 |
| abstract_inverted_index.NN-approximated | 97 |
| abstract_inverted_index.preconditioners | 13, 152 |
| abstract_inverted_index.($\mathcal{H}$-) | 107 |
| abstract_inverted_index.identifiability; | 65 |
| abstract_inverted_index.preconditioning. | 141 |
| abstract_inverted_index.multi-$\varepsilon$ | 67 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |