{"id":"https://openalex.org/W7208735167","doi":"https://doi.org/10.48550/arxiv.2609.03626","title":"Residual neural networks overcome the curse of dimensionality for semilinear heat equations","display_name":"Residual neural networks overcome the curse of dimensionality for semilinear heat equations","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208735167","doi":"https://doi.org/10.48550/arxiv.2609.03626"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03626","pdf_url":"https://arxiv.org/pdf/2609.03626","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.03626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141107020","display_name":"Ilkhom Mukhammadiev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mukhammadiev, Ilkhom","raw_affiliation_strings":["Department of Applied Mathematics , University of Freiburg , Germany;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics , University of Freiburg , Germany;","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075332945","display_name":"Diyora Salimova","orcid":"https://orcid.org/0000-0002-0111-5462","observed_orcids":["https://orcid.org/0000-0002-0111-5462"]},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Salimova, Diyora","raw_affiliation_strings":["Department of Applied Mathematics , University of Freiburg , Germany;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics , University of Freiburg , Germany;","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161046081"],"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":0.9585000276565552,"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":0.9585000276565552,"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/T10320","display_name":"Neural Networks and Applications","score":0.02630000002682209,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12404","display_name":"Mathematical Approximation and Integration","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.9980000257492065},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.996999979019165},{"id":"https://openalex.org/keywords/semilinear-heat-equation","display_name":"semilinear heat equation","score":0.9629999995231628},{"id":"https://openalex.org/keywords/high-dimensional-partial-differential-equations","display_name":"high-dimensional partial differential equations","score":0.7910000085830688},{"id":"https://openalex.org/keywords/skip-connections","display_name":"skip connections","score":0.578000009059906},{"id":"https://openalex.org/keywords/polynomial-growth","display_name":"polynomial growth","score":0.41499999165534973},{"id":"https://openalex.org/keywords/sigmoid-activation-function","display_name":"sigmoid activation function","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.8375999927520752},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.8220999836921692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7523999810218811},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.6133999824523926},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C202787564","wikidata":"https://www.wikidata.org/wiki/Q6510488","display_name":"Heat equation","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C107393986","wikidata":"https://www.wikidata.org/wiki/Q11912046","display_name":"Change of variables (PDE)","level":5,"score":0.2696000039577484},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.03626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03626","pdf_url":"https://arxiv.org/pdf/2609.03626","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.03626","doi":"https://doi.org/10.48550/arxiv.2609.03626","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03626","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03626","pdf_url":"https://arxiv.org/pdf/2609.03626","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3547540627","display_name":null,"funder_award_id":"SFB1597","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8615871816","display_name":"SFB 1597: Small Data","funder_award_id":"499552394","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208735167.pdf","grobid_xml":"https://content.openalex.org/works/W7208735167.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3083166268","https://openalex.org/W4281762554","https://openalex.org/W4387075655","https://openalex.org/W4399794620"],"related_works":["https://openalex.org/W2923153053","https://openalex.org/W4409353494","https://openalex.org/W3208986828","https://openalex.org/W4281762554","https://openalex.org/W4399794620","https://openalex.org/W4406808399","https://openalex.org/W4403815807","https://openalex.org/W2991444716","https://openalex.org/W4387075655","https://openalex.org/W7094136228"],"abstract_inverted_index":{"Rigorous":[0],"results":[1],"show":[2],"that":[3,40],"feedforward":[4],"neural":[5,30],"networks":[6,31],"can":[7],"overcome":[8,42],"the":[9,14,34,43,48,71,90,120,128,133,136,150,157,162],"curse":[10,44],"of":[11,17,45,51,53,98,108,135,149,164],"dimensionality":[12,46],"in":[13,33,47,92],"numerical":[15,49],"approximation":[16,50],"high-dimensional":[18],"partial":[19],"differential":[20],"equations":[21,56],"(PDEs),":[22],"but":[23],"comparatively":[24],"little":[25],"is":[26],"known":[27],"about":[28],"residual":[29,129],"(ResNets)":[32],"nonlinear":[35],"PDE":[36,72],"setting.":[37],"We":[38],"prove":[39],"ResNets":[41,78],"solutions":[52],"semilinear":[54],"heat":[55],"with":[57,82,95],"globally":[58,146],"Lipschitz":[59,147],"continuous,":[60],"gradient-independent":[61],"nonlinearities:":[62],"under":[63],"polynomial":[64],"growth":[65],"and":[66,77,123,145],"network":[67],"approximability":[68],"hypotheses":[69],"on":[70,161],"data,":[73],"there":[74],"exist":[75],"$\u03b7\\in(0,\\infty)$":[76],"$\u03a8_{d,\\varepsilon}$,":[79],"$d\\in\\mathbb{N}$,":[80],"$\\varepsilon\\in(0,1]$,":[81],"at":[83,99],"most":[84,100],"$\u03b7d^\u03b7\\varepsilon^{-\u03b7}$":[85],"parameters":[86],"whose":[87,116],"realizations":[88],"approximate":[89],"solution":[91],"dimension":[93],"$d$":[94],"an":[96],"$L^2$-error":[97],"$\\varepsilon$.":[101],"The":[102],"proof":[103],"represents":[104],"one":[105],"deterministic":[106],"realization":[107],"a":[109,114,124],"multilevel":[110],"Picard":[111],"estimator":[112],"by":[113],"ResNet":[115],"shortcut":[117],"connections":[118],"transmit":[119],"spatial":[121],"variable":[122],"scalar":[125],"accumulator,":[126],"while":[127],"branches":[130],"successively":[131],"add":[132],"summands":[134],"estimator.":[137],"For":[138],"ridge-sum":[139],"initial":[140],"conditions,":[141],"admissible":[142],"sigmoidal":[143],"activations,":[144],"truncations":[148],"nonlinearity,":[151],"we":[152],"obtain,":[153],"for":[154],"every":[155],"$\u03be>0$,":[156],"explicit":[158],"bound":[159],"$C_\u03bed^{4+\u03be}\\varepsilon^{-(3+\u03be)}$":[160],"number":[163],"parameters.":[165]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-05T00:00:00"}