{"id":"https://openalex.org/W7140278486","doi":"https://doi.org/10.48550/arxiv.2603.23072","title":"Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations","display_name":"Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140278486","doi":"https://doi.org/10.48550/arxiv.2603.23072"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f340c36c-dd1e-4bea-af17-38b32f70a528","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f340c36c-dd1e-4bea-af17-38b32f70a528","pdf_url":"https://pure.manchester.ac.uk/ws/files/1865252053/2603.23072v1.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andre-Sloan, S, Kumar, D, Frangi, A F & Mukherjee, A 2026 'Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations' arXiv. https://doi.org/10.48550/arXiv.2603.23072","raw_type":"info:eu-repo/semantics/preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.manchester.ac.uk/ws/files/1865252053/2603.23072v1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130570554","display_name":"Sebastien Andre-Sloan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andre-Sloan, Sebastien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861102","display_name":"Dibyakanti Kumar","orcid":"https://orcid.org/0009-0009-7864-5865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Dibyakanti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049192404","display_name":"Alejandro F. Frangi","orcid":"https://orcid.org/0000-0002-2675-528X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frangi, Alejandro F","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084835559","display_name":"Anirbit Mukherjee","orcid":"https://orcid.org/0000-0001-5189-8939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherjee, Anirbit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7013999819755554},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6672999858856201},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6266000270843506},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.486299991607666},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.3422999978065491}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7013999819755554},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6672999858856201},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6266000270843506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6068999767303467},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C84655787","wikidata":"https://www.wikidata.org/wiki/Q8067817","display_name":"Compressibility","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29750001430511475},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.258899986743927},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f340c36c-dd1e-4bea-af17-38b32f70a528","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f340c36c-dd1e-4bea-af17-38b32f70a528","pdf_url":"https://pure.manchester.ac.uk/ws/files/1865252053/2603.23072v1.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andre-Sloan, S, Kumar, D, Frangi, A F & Mukherjee, A 2026 'Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations' arXiv. https://doi.org/10.48550/arXiv.2603.23072","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2603.23072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f340c36c-dd1e-4bea-af17-38b32f70a528","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f340c36c-dd1e-4bea-af17-38b32f70a528","pdf_url":"https://pure.manchester.ac.uk/ws/files/1865252053/2603.23072v1.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andre-Sloan, S, Kumar, D, Frangi, A F & Mukherjee, A 2026 'Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations' arXiv. https://doi.org/10.48550/arXiv.2603.23072","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140278486.pdf","grobid_xml":"https://content.openalex.org/works/W7140278486.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,37],"work":[1],"establishes":[2],"rigorous":[3],"first-of-its-kind":[4],"upper":[5],"bounds":[6,58,91,96,118],"on":[7,63,119],"the":[8,12,18,30,42,46,64,71,77,87,111,116,124],"generalization":[9,57,72,95],"error":[10],"for":[11,102],"method":[13],"of":[14,45,76,110],"approximating":[15],"solutions":[16],"to":[17],"(d+1)-dimensional":[19],"incompressible":[20],"Navier-Stokes":[21],"equations":[22],"by":[23,40],"training":[24],"depth-2":[25],"neural":[26],"networks":[27],"trained":[28],"via":[29],"unsupervised":[31],"Physics-Informed":[32],"Neural":[33],"Network":[34],"(PINN)":[35],"framework.":[36],"is":[38],"achieved":[39],"bounding":[41],"Rademacher":[43],"complexity":[44,90],"PINN":[47,121],"risk.":[48],"For":[49],"appropriately":[50],"weight":[51],"bounded":[52],"net":[53],"classes":[54],"our":[55,68],"derived":[56],"do":[59],"not":[60],"explicitly":[61],"depend":[62],"network":[65],"width":[66],"and":[67,81,115],"framework":[69],"characterizes":[70],"gap":[73],"in":[74],"terms":[75],"fluid's":[78],"kinematic":[79],"viscosity":[80],"loss":[82],"regularization":[83],"parameters.":[84],"In":[85],"particular,":[86],"resulting":[88],"sample":[89],"are":[92],"dimension-independent.":[93],"Our":[94],"suggest":[97],"using":[98],"novel":[99],"activation":[100,113],"functions":[101,114],"solving":[103,123],"fluid":[104],"dynamics.":[105],"We":[106],"provide":[107],"empirical":[108],"validation":[109],"suggested":[112],"corresponding":[117],"a":[120],"setup":[122],"Taylor-Green":[125],"vortex":[126],"benchmark.":[127]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-03-26T00:00:00"}