{"id":"https://openalex.org/W7114900118","doi":"https://doi.org/10.1109/lsp.2025.3643361","title":"Shallow Neural Network Training via Atomic Norms and Semidefinite Programming","display_name":"Shallow Neural Network Training via Atomic Norms and Semidefinite Programming","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W7114900118","doi":"https://doi.org/10.1109/lsp.2025.3643361"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3643361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3643361","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Andrew J. Christensen","orcid":"https://orcid.org/0009-0009-9636-0126"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew J. Christensen","raw_affiliation_strings":["Department of Electrical, and Computer Engineering, University of Iowa, Iowa City, IA, USA"],"raw_orcid":"https://orcid.org/0009-0009-9636-0126","affiliations":[{"raw_affiliation_string":"Department of Electrical, and Computer Engineering, University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ananya Sen Gupta","orcid":"https://orcid.org/0000-0001-5255-8493"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananya Sen Gupta","raw_affiliation_strings":["Department of Electrical, and Computer Engineering, University of Iowa, Iowa City, IA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5255-8493","affiliations":[{"raw_affiliation_string":"Department of Electrical, and Computer Engineering, University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126307644"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73011868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"321","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3043000102043152,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3043000102043152,"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":0.1665000021457672,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.060100000351667404,"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/semidefinite-programming","display_name":"Semidefinite programming","score":0.7324000000953674},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6205999851226807},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.592199981212616},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5863000154495239},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.49219998717308044},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.483599990606308},{"id":"https://openalex.org/keywords/matrix-norm","display_name":"Matrix norm","score":0.4325999915599823},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.424699991941452},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4124000072479248}],"concepts":[{"id":"https://openalex.org/C101901036","wikidata":"https://www.wikidata.org/wiki/Q2269096","display_name":"Semidefinite programming","level":2,"score":0.7324000000953674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.592199981212616},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849000215530396},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5135999917984009},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2985999882221222},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3643361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3643361","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4803781311","display_name":null,"funder_award_id":"N000142312503","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1822012234","https://openalex.org/W1966096622","https://openalex.org/W2020255126","https://openalex.org/W2028191993","https://openalex.org/W2045983409","https://openalex.org/W2047071281","https://openalex.org/W2093328751","https://openalex.org/W2103972604","https://openalex.org/W2117377454","https://openalex.org/W2118550318","https://openalex.org/W2119667497","https://openalex.org/W2124608575","https://openalex.org/W2135046866","https://openalex.org/W2138019504","https://openalex.org/W2140867429","https://openalex.org/W2145962650","https://openalex.org/W2167077875","https://openalex.org/W2168903001","https://openalex.org/W2288174618","https://openalex.org/W2565293665","https://openalex.org/W2912522929","https://openalex.org/W3010499839","https://openalex.org/W3210839039","https://openalex.org/W4404164820","https://openalex.org/W4407938032"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"networks":[1,23,46,80,101],"have":[2],"achieved":[3,145],"remarkable":[4],"results":[5,120],"across":[6],"numerous":[7],"scientific":[8],"domains":[9],"because":[10],"of":[11,28,99],"their":[12,20],"ability":[13],"to":[14,137,153],"uncover":[15],"complex":[16],"patterns.":[17],"However,":[18],"despite":[19],"effectiveness,":[21],"these":[22],"rely":[24],"on":[25,82],"heuristic":[26,139],"training":[27,125],"highly":[29],"non-convex":[30],"objective":[31],"functions,":[32],"limiting":[33],"theoretical":[34],"understanding":[35],"and":[36,86,106,129],"practical":[37],"reliability.":[38],"Recent":[39],"work":[40],"has":[41],"shown":[42],"that":[43,102],"shallow":[44],"neural":[45,123],"with":[47,60],"scalar":[48,127],"outputs":[49,128],"can":[50],"be":[51],"formulated":[52],"as":[53,88],"convex":[54,75,97,122,156],"optimization":[55],"problems,":[56],"bridging":[57],"empirical":[58],"success":[59],"theory.":[61],"In":[62],"this":[63,68],"work,":[64],"we":[65],"build":[66],"upon":[67],"framework":[69],"for":[70,77,133],"vector-valued":[71],"outputs,":[72],"introducing":[73],"a":[74,89,95,131,146,154],"formulation":[76],"two-layer":[78],"ReLU":[79],"based":[81],"an":[83],"atomic":[84],"norm":[85],"expressible":[87],"semidefinite":[90],"program":[91],"(SDP).":[92],"This":[93],"yields":[94],"principled":[96],"relaxation":[98],"multi-output":[100,157],"is":[103],"both":[104],"expressive":[105],"tractable.":[107],"We":[108],"validate":[109],"the":[110],"approach":[111],"using":[112],"standard":[113],"SDP":[114],"solvers,":[115],"demonstrating":[116],"its":[117],"feasibility.":[118],"These":[119],"extend":[121],"network":[124],"beyond":[126],"provide":[130],"foundation":[132],"scalable,":[134],"robust":[135],"alternatives":[136],"current":[138],"deep":[140],"learning":[141],"methods.":[142],"Our":[143],"method":[144],"7.3%":[147],"increase":[148],"in":[149],"classification":[150],"accuracy":[151],"compared":[152],"baseline":[155],"network.":[158]},"counts_by_year":[],"updated_date":"2025-12-31T23:11:33.660297","created_date":"2025-12-12T00:00:00"}