{"id":"https://openalex.org/W4412404316","doi":"https://doi.org/10.1109/tit.2025.3588401","title":"On the Convergence of (Stochastic) Gradient Descent for Kolmogorov\u2013Arnold Networks","display_name":"On the Convergence of (Stochastic) Gradient Descent for Kolmogorov\u2013Arnold Networks","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412404316","doi":"https://doi.org/10.1109/tit.2025.3588401"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2025.3588401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3588401","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000346986","display_name":"Yihang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yihang Gao","raw_affiliation_strings":["Department of Mathematics, National University of Singapore, Queenstown, Singapore","Department of Mathematics, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Mathematics, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058345431","display_name":"Vincent Y. F. Tan","orcid":"https://orcid.org/0000-0002-5008-4527"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Vincent Y. F. Tan","raw_affiliation_strings":["Department of Mathematics, Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","Department of Mathematics, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5008-4527","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Mathematics, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":7.0959,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97243226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"71","issue":"9","first_page":"7270","last_page":"7291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11022","display_name":"Spectral Theory in Mathematical Physics","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11022","display_name":"Spectral Theory in Mathematical Physics","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"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/T11476","display_name":"Graph theory and applications","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/convergence","display_name":"Convergence (economics)","score":0.5911077260971069},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5457446575164795},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4666208028793335},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.45860394835472107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4526214599609375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.400595486164093},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3671187162399292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22789713740348816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22688782215118408},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1535968780517578},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08002331852912903}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5911077260971069},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5457446575164795},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4666208028793335},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.45860394835472107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4526214599609375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.400595486164093},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3671187162399292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22789713740348816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22688782215118408},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1535968780517578},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08002331852912903},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2025.3588401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3588401","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2009941369","https://openalex.org/W2062368570","https://openalex.org/W2546420264","https://openalex.org/W2566079294","https://openalex.org/W2963417959","https://openalex.org/W3021189130","https://openalex.org/W3117030766","https://openalex.org/W3205073660","https://openalex.org/W4226270271","https://openalex.org/W4238143865","https://openalex.org/W4244096624","https://openalex.org/W4396878152","https://openalex.org/W4396944743","https://openalex.org/W4398159307","https://openalex.org/W4399425292","https://openalex.org/W4399911929","https://openalex.org/W4399912438","https://openalex.org/W4402466802","https://openalex.org/W4403622498","https://openalex.org/W4404468356","https://openalex.org/W4404627985","https://openalex.org/W4405180437","https://openalex.org/W4406308687","https://openalex.org/W4406366950","https://openalex.org/W4408353412","https://openalex.org/W4409367393","https://openalex.org/W4411015042","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6678296350","https://openalex.org/W6681435938","https://openalex.org/W6712446393","https://openalex.org/W6737650911","https://openalex.org/W6737871451","https://openalex.org/W6739622702","https://openalex.org/W6739879593","https://openalex.org/W6747620207","https://openalex.org/W6751189704","https://openalex.org/W6752009368","https://openalex.org/W6752495264","https://openalex.org/W6753958361","https://openalex.org/W6755150206","https://openalex.org/W6755487116","https://openalex.org/W6756091659","https://openalex.org/W6802414854","https://openalex.org/W6838349824","https://openalex.org/W6860730913","https://openalex.org/W6867176674","https://openalex.org/W6869123291","https://openalex.org/W6869126553","https://openalex.org/W6869299805","https://openalex.org/W6869422220","https://openalex.org/W6869947743","https://openalex.org/W6870080900","https://openalex.org/W6870465529","https://openalex.org/W6870634262","https://openalex.org/W6871400773","https://openalex.org/W6872314343","https://openalex.org/W6872382153","https://openalex.org/W6872779373","https://openalex.org/W6873400135","https://openalex.org/W6891917580"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W1971945429","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Kolmogorov\u2013Arnold":[0],"Networks":[1],"(KANs),":[2],"a":[3,23,81,90,148],"recently":[4],"proposed":[5],"neural":[6,117],"network":[7],"architecture,":[8],"have":[9],"gained":[10],"significant":[11],"attention":[12],"in":[13,56,103,152],"the":[14,85,116,128,132,157,173,180,184],"deep":[15],"learning":[16,59],"community,":[17],"due":[18,171],"to":[19,26,34,145,172,193],"their":[20,31],"potential":[21],"as":[22],"viable":[24],"alternative":[25],"multi-layer":[27],"perceptrons":[28],"(MLPs)":[29],"and":[30,63,68,98,107,162,190,196],"broad":[32],"applicability":[33],"various":[35,57],"scientific":[36,69],"tasks.":[37,109],"Empirical":[38],"investigations":[39],"demonstrate":[40],"that":[41,121],"KANs":[42,102,136,195],"optimized":[43],"via":[44],"stochastic":[45],"gradient":[46,95],"descent":[47,96],"(SGD)":[48],"are":[49],"capable":[50],"of":[51,94,127,135,160],"achieving":[52],"near-zero":[53],"training":[54],"loss":[55,176],"machine":[58],"(e.g.,":[60,71],"regression,":[61],"classification,":[62],"time":[64],"series":[65],"forecasting,":[66],"etc.)":[67],"tasks":[70],"solving":[72,104],"partial":[73],"differential":[74],"equations).":[75],"In":[76],"this":[77],"paper,":[78],"we":[79,113,155],"provide":[80],"theoretical":[82],"explanation":[83],"for":[84,100,164,188],"empirical":[86],"success":[87],"by":[88],"conducting":[89],"rigorous":[91],"convergence":[92,126,151,159,186],"analysis":[93],"(GD)":[97],"SGD":[99,163,191],"two-layer":[101],"both":[105],"regression":[106,111],"physics-informed":[108,165,197],"For":[110],"problems,":[112],"establish":[114],"using":[115],"tangent":[118],"kernel":[119],"perspective":[120],"GD":[122,161,189],"achieves":[123],"global":[124,150,158,185],"linear":[125],"objective":[129],"function":[130],"when":[131],"hidden":[133],"dimension":[134],"is":[137,179],"sufficiently":[138],"large.":[139],"We":[140],"further":[141],"extend":[142],"these":[143],"results":[144],"SGD,":[146],"demonstrating":[147],"similar":[149],"expectation.":[153],"Additionally,":[154],"analyze":[156],"KANs,":[166],"which":[167],"unveils":[168],"additional":[169],"challenges":[170],"more":[174],"complex":[175],"structure.":[177],"This":[178],"first":[181],"work":[182],"establishing":[183],"guarantees":[187],"applied":[192],"optimize":[194],"KANs.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}