{"id":"https://openalex.org/W7214632773","doi":"https://doi.org/10.48550/arxiv.2609.30299","title":"Staged Depth Training: A Representation Curriculum for PINNs","display_name":"Staged Depth Training: A Representation Curriculum for PINNs","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7214632773","doi":"https://doi.org/10.48550/arxiv.2609.30299"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.30299","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30299","pdf_url":"https://arxiv.org/pdf/2609.30299","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/2609.30299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153278257","display_name":"Kejia Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Kejia","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153339151","display_name":"Youran Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Youran","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153195785","display_name":"Haizhao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Haizhao","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/physics-informed-neural-networks","display_name":"physics-informed neural networks","score":0.9980000257492065},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.4970000088214874},{"id":"https://openalex.org/keywords/network-depth","display_name":"network depth","score":0.45399999618530273},{"id":"https://openalex.org/keywords/hyperparameter-sensitivity","display_name":"hyperparameter sensitivity","score":0.5740000009536743},{"id":"https://openalex.org/keywords/poisson-boltzmann-equation","display_name":"Poisson-Boltzmann equation","score":0.8199999928474426},{"id":"https://openalex.org/keywords/representational-geometry","display_name":"representational geometry","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7950999736785889},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5372999906539917},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.313400000333786},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.30299","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30299","pdf_url":"https://arxiv.org/pdf/2609.30299","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.2609.30299","doi":"https://doi.org/10.48550/arxiv.2609.30299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.30299","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:2609.30299","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30299","pdf_url":"https://arxiv.org/pdf/2609.30299","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214632773.pdf","grobid_xml":"https://content.openalex.org/works/W7214632773.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4386794621","https://openalex.org/W7125712676","https://openalex.org/W7155352875"],"related_works":["https://openalex.org/W7006225656","https://openalex.org/W4400135156","https://openalex.org/W4309864903","https://openalex.org/W4385965970","https://openalex.org/W7161581154","https://openalex.org/W7170334922","https://openalex.org/W4307312252","https://openalex.org/W4327704331","https://openalex.org/W4389752819","https://openalex.org/W4412423516"],"abstract_inverted_index":{"Representation":[0,138],"quality":[1],"is":[2,128],"a":[3,53,57,113,119,176],"central":[4],"determinant":[5],"of":[6,37,95],"PINNs'":[7],"performance,":[8],"yet":[9],"standard":[10],"training":[11,178],"leaves":[12],"representations":[13,31],"to":[14,77,152],"emerge":[15],"implicitly":[16],"while":[17,69,183],"fitting":[18],"the":[19,62,66,78,82,110,126,163,185],"final":[20,79],"solution.":[21],"We":[22,43],"introduce":[23],"\\textbf{representation":[24],"curriculum},":[25],"an":[26],"ordered":[27],"process":[28],"in":[29,87,109],"which":[30,51],"are":[32],"explicitly":[33],"learned,":[34],"transferred":[35],"independently":[36],"their":[38],"predictors,":[39],"and":[40,64,104,140,149,188],"progressively":[41],"refined.":[42],"realize":[44],"it":[45],"with":[46,89,112],"Staged":[47],"Depth":[48],"Training":[49],"(SDT),":[50],"trains":[52],"shallow":[54,135],"prefix":[55,68],"under":[56],"temporary":[58],"physics-informed":[59],"head,":[60,63],"discards":[61],"freezes":[65],"learned":[67],"adding":[70],"depth,":[71],"without":[72],"equation-specific":[73],"encodings":[74],"or":[75,134],"changes":[76],"architecture.":[80],"Across":[81],"20":[83],"default":[84],"forward":[85],"problems":[86],"PINNacle":[88],"three":[90],"backbones,":[91],"SDT":[92,158],"improves":[93],"40":[94],"59":[96],"equal-budget":[97],"problem--backbone":[98],"cells":[99],"by":[100,131],"at":[101],"least":[102],"5\\%":[103],"remains":[105],"within":[106],"that":[107,125],"band":[108],"rest,":[111],"32.8\\%":[114],"geometric-mean":[115],"error":[116],"reduction":[117],"on":[118,146],"PirateNet-style":[120],"backbone.":[121],"Mechanistic":[122],"ablations":[123],"suggest":[124],"gain":[127],"not":[129],"explained":[130],"optimizer":[132],"restarts":[133],"warm-starting":[136],"alone.":[137],"visualizations":[139],"hyperparameter-basin":[141],"analyses":[142],"provide":[143],"diagnostic":[144],"evidence":[145],"representation":[147,173],"geometry":[148],"local":[150],"sensitivity":[151],"shared":[153],"hyperparameters.":[154],"On":[155],"Poisson--Boltzmann":[156],"2D,":[157],"also":[159],"more":[160],"than":[161],"doubles":[162],"fitted":[164],"depth-scaling":[165],"exponent":[166],"for":[167,180],"both":[168],"backbones.":[169],"These":[170],"results":[171],"support":[172],"curriculum":[174],"as":[175],"promising":[177],"strategy":[179],"improving":[181],"PINNs":[182],"preserving":[184],"deployed":[186],"architecture":[187],"inference":[189],"cost.":[190]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-29T00:00:00"}