{"id":"https://openalex.org/W7140075317","doi":"https://doi.org/10.1109/tsp.2026.3676735","title":"Convergence Theory of Sharpness-Aware Minimization With Interpolating Neural Networks","display_name":"Convergence Theory of Sharpness-Aware Minimization With Interpolating Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140075317","doi":"https://doi.org/10.1109/tsp.2026.3676735"},"language":null,"primary_location":{"id":"doi:10.1109/tsp.2026.3676735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2026.3676735","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","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/A5130341254","display_name":"Tan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Sun","raw_affiliation_strings":["Center for Data Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-6640-7684","affiliations":[{"raw_affiliation_string":"Center for Data Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104194387","display_name":"Yusu Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusu Hong","raw_affiliation_strings":["Center for Data Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9418-3095","affiliations":[{"raw_affiliation_string":"Center for Data Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017897576","display_name":"Junhong Lin","orcid":"https://orcid.org/0000-0003-3869-1380"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Lin","raw_affiliation_strings":["Center for Data Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4507-9424","affiliations":[{"raw_affiliation_string":"Center for Data Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29646987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":null,"first_page":"1491","last_page":"1507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.1378999948501587,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.1378999948501587,"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/T12676","display_name":"Machine Learning and ELM","score":0.052799999713897705,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.03819999843835831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6323000192642212},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6060000061988831},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5776000022888184},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.41769999265670776},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.3853999972343445},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.2840000092983246}],"concepts":[{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6060000061988831},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5041000247001648},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3986000120639801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3871000111103058},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C2988922011","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering theory","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2026.3676735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2026.3676735","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4335637092590332,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5887349971","display_name":null,"funder_award_id":"12471096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"theoretical":[2],"analysis":[3,81],"of":[4,39,49,58,78,86,179],"Sharpness-Aware":[5],"Minimization":[6],"(SAM)":[7],"applied":[8],"to":[9,44,160],"training":[10,59,188],"loss":[11,42,64,169,189],"minimization":[12],"with":[13,32,136,143],"neural":[14,40,68,92,118,133,185],"networks":[15,119,134,186],"and":[16,66,89,148],"smooth":[17,29,63,98],"activations.":[18],"Unlike":[19],"prior":[20],"works":[21],"on":[22,83,187],"stationary":[23],"points":[24],"measure":[25],"in":[26,184],"standard":[27],"non-convex":[28],"optimization":[30,94],"settings":[31],"noise":[33],"assumptions,":[34],"we":[35],"leverage":[36],"intrinsic":[37],"properties":[38,85],"network":[41,93],"landscapes":[43],"establish":[45],"a":[46,137,144,149],"convergence":[47],"rate":[48,147],"\u00d5<inline-formula":[50],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51,72,107,122,162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[52,108,123,163],"notation=\"LaTeX\">$(1/T":[53],")$</tex-math></inline-formula>":[54,115,130],"for":[55,116,131,166,182],"the":[56,62,75,84,104,167,177],"average":[57],"loss,":[60],"under":[61],"function":[65],"interpolating":[67],"networks.":[69],"Here,":[70],"<italic":[71],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</i>":[73],"is":[74],"total":[76],"number":[77],"iterations.":[79],"Our":[80,100],"lies":[82],"self-bounded-like":[87],"gradients":[88],"Hessians,":[90],"distinguishing":[91],"from":[95],"general":[96],"nonconvex":[97],"optimization.":[99],"results":[101,175],"require":[102],"that":[103],"width":[105,154],"<inline-formula":[106,121,161],"notation=\"LaTeX\">$m":[109,124,164],"\\ge":[110,125],"\\tilde":[111,126],"\\Omega":[112,127],"(":[113],"T":[114,129],"shallow":[117],"while":[120],"(\\sqrt":[128],"deep":[132],"(though":[135],"minor":[138],"different":[139],"scaling":[140],"architecture),":[141],"both":[142],"constant":[145],"learning":[146],"small":[150],"perturbation":[151],"parameter.":[152],"The":[153],"requirement":[155],"can":[156],"be":[157],"further":[158],"reduced":[159],"\u2265$</tex-math></inline-formula>\u00d5(1)":[165],"logistic":[168],"function.":[170],"To":[171],"our":[172,174],"knowledge,":[173],"are":[176],"first":[178],"its":[180],"kinds":[181],"SAM":[183],"bounds.":[190]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2026-03-24T00:00:00"}