{"id":"https://openalex.org/W7162132370","doi":"https://doi.org/10.48550/arxiv.2605.22182","title":"IKNO: Infinite-order Kernel Neural Operators","display_name":"IKNO: Infinite-order Kernel Neural Operators","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162132370","doi":"https://doi.org/10.48550/arxiv.2605.22182"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.22182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136781160","display_name":"Pengyuan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Pengyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136811135","display_name":"Ivor W. Tsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang, Ivor W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136783487","display_name":"Yueming Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Yueming","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":false,"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":0.5271999835968018,"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":0.5271999835968018,"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/T12303","display_name":"Tensor decomposition and applications","score":0.24009999632835388,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.07590000331401825,"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/kernel","display_name":"Kernel (algebra)","score":0.6912999749183655},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5224000215530396},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4887000024318695},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42910000681877136},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4226999878883362},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4090999960899353},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5803999900817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5375999808311462},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45509999990463257},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4049000144004822},{"id":"https://openalex.org/C196267783","wikidata":"https://www.wikidata.org/wiki/Q4392490","display_name":"Resolvent","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C46030957","wikidata":"https://www.wikidata.org/wiki/Q1238125","display_name":"Kronecker product","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.46010440587997437,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0,41],"operators":[1,47],"have":[2],"achieved":[3],"significant":[4,144],"success":[5],"in":[6],"modern":[7],"scientific":[8],"computing":[9],"due":[10],"to":[11,154],"their":[12,31],"flexibility":[13],"and":[14,52,80,120],"strong":[15],"generalization":[16],"capabilities.":[17],"Existing":[18],"models,":[19],"however,":[20],"primarily":[21],"rely":[22],"on":[23,73,117,146],"first-order":[24],"kernel":[25,50],"integral":[26],"approximations,":[27],"which":[28,44,68,101],"severely":[29],"limit":[30],"expressivity.":[32],"To":[33],"address":[34],"this,":[35],"we":[36,91,113],"propose":[37],"the":[38,70,74,135,140],"Infinite-order":[39],"Kernel":[40],"Operator":[42],"(IKNO),":[43],"constructs":[45],"neural":[46,64],"via":[48,77],"infinite-order":[49,63],"integrals":[51],"admits":[53],"an":[54,82],"elegant":[55],"closed-form":[56],"finite":[57],"approximation.":[58],"We":[59],"develop":[60,92],"two":[61],"complementary":[62],"operator":[65,85],"constructions:":[66],"IKNO-Vanilla,":[67],"applies":[69],"full-kernel":[71],"resolvent":[72],"product":[75],"grid":[76],"Kronecker":[78],"eigendecomposition,":[79],"IKNO-TP,":[81],"alternative":[83],"tensor-product":[84],"that":[86,134],"composes":[87],"per-axis":[88],"resolvents.":[89],"Furthermore,":[90],"fast":[93],"computation":[94],"schemes":[95],"for":[96],"both":[97,118],"variants":[98],"of":[99],"IKNO,":[100],"achieve":[102],"outstanding":[103],"global":[104],"information":[105],"aggregation":[106],"while":[107,151],"maintaining":[108,152],"high":[109],"computational":[110],"efficiency.":[111],"Empirically,":[112],"evaluate":[114],"our":[115],"IKNO":[116,136],"time-dependent":[119],"time-independent":[121],"benchmarks":[122],"with":[123,143],"arbitrary":[124],"input":[125],"shapes,":[126],"including":[127],"large-scale":[128],"industrial":[129],"datasets.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"method":[137],"consistently":[138],"achieves":[139],"SOTA":[141],"accuracy":[142],"improvements":[145],"nearly":[147],"all":[148],"benchmark":[149],"datasets":[150],"scalability":[153],"very":[155],"large":[156],"point":[157],"clouds.":[158]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}