{"id":"https://openalex.org/W7148263828","doi":"https://doi.org/10.48550/arxiv.2604.00505","title":"Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks","display_name":"Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148263828","doi":"https://doi.org/10.48550/arxiv.2604.00505"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.00505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00505","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.00505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046468616","display_name":"Yunwen Lei","orcid":"https://orcid.org/0000-0002-5383-467X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Yunwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132791962","display_name":"Yufeng Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yufeng","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.824400007724762,"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":0.824400007724762,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03220000118017197,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/overfitting","display_name":"Overfitting","score":0.8328999876976013},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7630000114440918},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.7497000098228455},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6625999808311462},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5655999779701233},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5565000176429749}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8328999876976013},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7630000114440918},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.7497000098228455},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5101000070571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4372999966144562},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2687000036239624}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.00505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00505","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.00505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00505","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Overparameterized":[0],"neural":[1,97],"networks":[2,98],"often":[3,55,78],"show":[4,151],"a":[5,120,136,142],"benign":[6,33],"overfitting":[7,34],"property":[8],"in":[9,82],"the":[10,18,23,40,48,59,63,69,74,108,111,126,130],"sense":[11],"of":[12,20,25,42,110],"achieving":[13],"excellent":[14],"generalization":[15,38,154],"behavior":[16],"despite":[17],"number":[19,24],"parameters":[21],"exceeding":[22],"training":[26],"examples.":[27],"A":[28],"promising":[29],"direction":[30],"to":[31,36,39,124,141],"explain":[32],"is":[35,54],"relate":[37],"norm":[41,60],"distance":[43,53,70,112],"from":[44,71,113],"initialization,":[45,114],"motivated":[46],"by":[47,73,118],"empirical":[49,148],"observations":[50],"that":[51,152],"this":[52,88],"significantly":[56],"smaller":[57],"than":[58],"itself.":[61],"However,":[62],"existing":[64],"initialization-dependent":[65,92,131],"complexity":[66,93],"analyses":[67],"measure":[68],"initialization":[72],"Frobenius":[75],"norm,":[76],"and":[77,150],"imply":[79],"vacuous":[80],"bounds":[81,94,105,158],"practice":[83],"for":[84,95,159],"overparamterized":[85],"models.":[86],"In":[87],"paper,":[89],"we":[90,146],"develop":[91,135],"shallow":[96],"with":[99,129],"general":[100],"Lipschitz":[101],"activation":[102],"functions.":[103],"Our":[104],"depend":[106],"on":[107],"path-norm":[109],"which":[115],"are":[116],"derived":[117],"introducing":[119],"new":[121],"peeling":[122],"technique":[123],"handle":[125],"challenge":[127],"along":[128],"constraint.":[132],"We":[133],"also":[134],"lower":[137],"bound":[138],"tight":[139],"up":[140],"constant":[143],"factor.":[144],"Finally,":[145],"conduct":[147],"comparisons":[149],"our":[153],"analysis":[155],"implies":[156],"non-vacuous":[157],"overparameterized":[160],"networks.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-03T00:00:00"}