{"id":"https://openalex.org/W7236409376","doi":"https://doi.org/10.48550/arxiv.2611.22236","title":"Spatially local mini-batching for implicit neural representations","display_name":"Spatially local mini-batching for implicit neural representations","alternate_titles":[],"publication_year":2026,"publication_date":"2026-11-17","ids":{"openalex":"https://openalex.org/W7236409376","doi":"https://doi.org/10.48550/arxiv.2611.22236"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.22236","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.22236","pdf_url":"https://arxiv.org/pdf/2611.22236","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"},"parent_works":[],"lineage":["https://openalex.org/W7236409376"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.22236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157852070","display_name":"Minseok Choi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Choi, Minseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084758457","display_name":"Swarup Dhar","orcid":"https://orcid.org/0000-0002-6482-5816","observed_orcids":["https://orcid.org/0000-0002-6482-5816"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Dhar, Swarup","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548545","display_name":"H. Kwon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Kwon, Heejae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5162786061","display_name":"Kookjin Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Lee, Kookjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000029200","display_name":"Donsub Rim","orcid":"https://orcid.org/0000-0002-6721-2070","observed_orcids":["https://orcid.org/0000-0002-6721-2070"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Rim, Donsub","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,"reviewed_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_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/implicit-neural-representations","display_name":"implicit neural representations","score":0.9929999709129333},{"id":"https://openalex.org/keywords/hypernetworks","display_name":"hypernetworks","score":0.7580000162124634},{"id":"https://openalex.org/keywords/adaptive-mesh-refinement","display_name":"adaptive mesh refinement","score":0.9020000100135803},{"id":"https://openalex.org/keywords/kolmogorov-widths","display_name":"Kolmogorov widths","score":0.8730000257492065},{"id":"https://openalex.org/keywords/hyperbolic-conservation-laws","display_name":"hyperbolic conservation laws","score":0.8889999985694885},{"id":"https://openalex.org/keywords/deeponet","display_name":"DeepONet","score":0.9440000057220459},{"id":"https://openalex.org/keywords/fourier-neural-operator","display_name":"Fourier neural operator","score":0.9639999866485596},{"id":"https://openalex.org/keywords/neural-network-surrogate-model","display_name":"neural network surrogate model","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256999969482422},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6129000186920166},{"id":"https://openalex.org/C2777588356","wikidata":"https://www.wikidata.org/wiki/Q1868414","display_name":"Local property","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5462999939918518},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4025999903678894},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C2986090443","wikidata":"https://www.wikidata.org/wiki/Q77870413","display_name":"Local structure","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33390000462532043},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2778740170","wikidata":"https://www.wikidata.org/wiki/Q7575210","display_name":"Spectral space","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.22236","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.22236","pdf_url":"https://arxiv.org/pdf/2611.22236","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.2611.22236","doi":"https://doi.org/10.48550/arxiv.2611.22236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.22236","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:2611.22236","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.22236","pdf_url":"https://arxiv.org/pdf/2611.22236","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309650","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7236409376.pdf","grobid_xml":"https://content.openalex.org/works/W7236409376.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1555627060","https://openalex.org/W1977029864","https://openalex.org/W2025483160","https://openalex.org/W2047591100","https://openalex.org/W2049753327","https://openalex.org/W2077047259","https://openalex.org/W2087087179","https://openalex.org/W2092891737","https://openalex.org/W2162287622","https://openalex.org/W2292527387","https://openalex.org/W2495959456","https://openalex.org/W2612526254","https://openalex.org/W2735791542","https://openalex.org/W2772645432","https://openalex.org/W2792287754","https://openalex.org/W2899283552","https://openalex.org/W2905589030","https://openalex.org/W2936544000","https://openalex.org/W2945827377","https://openalex.org/W2953795851","https://openalex.org/W2957969499","https://openalex.org/W2979786244","https://openalex.org/W2992541290","https://openalex.org/W3011806874","https://openalex.org/W3012728190","https://openalex.org/W3013987637","https://openalex.org/W3015865829","https://openalex.org/W3036234074","https://openalex.org/W3098546160","https://openalex.org/W3100990647","https://openalex.org/W3136202831","https://openalex.org/W3156609952","https://openalex.org/W3180799285","https://openalex.org/W3184908771","https://openalex.org/W3200673624","https://openalex.org/W4221151978","https://openalex.org/W4287978829","https://openalex.org/W4292169137","https://openalex.org/W4299521717","https://openalex.org/W4307154444","https://openalex.org/W4387929099","https://openalex.org/W4399555033","https://openalex.org/W4399840403","https://openalex.org/W4407565137","https://openalex.org/W6903388168","https://openalex.org/W7102621427","https://openalex.org/W7133183825","https://openalex.org/W7160289500","https://openalex.org/W7213612741"],"related_works":["https://openalex.org/W7128502427","https://openalex.org/W7130337722","https://openalex.org/W7127387832","https://openalex.org/W7225729001","https://openalex.org/W7133183752","https://openalex.org/W4417468039","https://openalex.org/W4399424853","https://openalex.org/W7212372969","https://openalex.org/W4302010416"],"abstract_inverted_index":{"Neural":[0],"surrogates":[1],"based":[2],"on":[3,11,255],"implicit":[4],"neural":[5,39,217],"representations":[6,40],"(INRs)":[7],"are":[8,46],"typically":[9],"trained":[10,60],"mini-batches":[12],"spread":[13],"over":[14],"the":[15,68,90,93,103,113,118,130,145,158,166,193,200,221,225,240,256],"whole":[16],"domain,":[17],"since":[18],"a":[19,28,55,109,133,142,153,190,196,206,210,212,215,252,262],"generic":[20,264],"INR":[21],"loses":[22],"accuracy":[23],"when":[24,139],"every":[25],"point":[26],"of":[27,48,70,74,92,106,121,148,165,192,195,199,220],"batch":[29],"lies":[30],"in":[31,261],"one":[32,71,80,126,180],"small":[33,56,81,143],"region.":[34],"We":[35,95,232],"show":[36,137],"that":[37,97,138,234,248],"low-rank":[38,163],"(LRNRs),":[41],"INRs":[42],"whose":[43],"weight":[44],"matrices":[45],"products":[47],"shared":[49,114,167],"bases":[50,115],"with":[51,61,83,173,189,224],"coefficients":[52,120],"emitted":[53],"by":[54,102,208],"hypernetwork,":[57],"can":[58],"be":[59],"spatially":[62],"local":[63,110,159,181,227,249],"mini-batches.":[64],"Each":[65],"step":[66,111],"uses":[67],"points":[69],"time":[72],"snapshot":[73],"an":[75],"adaptive-mesh":[76],"numerical":[77],"solution":[78],"inside":[79],"cell,":[82,144],"snapshots":[84],"and":[85,124,214,229],"cells":[86],"drawn":[87],"according":[88],"to":[89,141,152],"refinement":[91],"mesh.":[94],"posit":[96],"such":[98],"training":[99,182,209,230,250],"is":[100],"enabled":[101],"structural":[104],"property":[105],"LRNRs,":[107],"as":[108],"reaches":[112,184,242],"only":[116,161],"through":[117],"$r$":[119],"each":[122],"layer,":[123],"keeps":[125],"cell":[127],"from":[128],"rewriting":[129],"network.":[131],"By":[132],"Kolmogorov-width":[134],"argument,":[135],"we":[136,204,245],"restricted":[140],"hidden":[146],"states":[147],"LRNRs":[149],"lie":[150],"close":[151],"low-dimensional":[154,258],"subspace,":[155],"which":[156],"suggests":[157],"steps":[160],"affect":[162],"subspaces":[164],"bases.":[168],"On":[169],"six":[170],"hyperbolic-conservation-law":[171],"problems":[172],"solutions":[174],"computed":[175],"using":[176],"adaptive":[177],"mesh":[178],"refinement,":[179],"recipe":[183],"1.1-2.3%":[185],"relative":[186],"$L^2$":[187],"error":[188],"tenth":[191],"parameters":[194],"dense":[197],"network":[198],"same":[201,222,226],"width.":[202],"Finally,":[203],"provide":[205],"comparison":[207],"hypernetwork-SIREN,":[211],"DeepONet,":[213],"Fourier":[216],"operator":[218],"(FNO)":[219],"size":[223],"batches":[228],"budget.":[231],"observe":[233,247],"these":[235],"baselines":[236],"reach":[237],"16-78%":[238],"where":[239],"LRNR":[241],"4.9%.":[243],"Interestingly,":[244],"also":[246],"has":[251],"significant":[253],"effect":[254],"per-cell":[257],"structure":[259],"even":[260],"wide":[263],"hypernetwork-SIREN.":[265]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7236409376","counts_by_year":[],"updated_date":"2026-11-22T12:46:00.618207","created_date":"2026-11-19T00:00:00"}
