{"id":"https://openalex.org/W7131395916","doi":"https://doi.org/10.48550/arxiv.2602.18825","title":"Bayesian Lottery Ticket Hypothesis","display_name":"Bayesian Lottery Ticket Hypothesis","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7131395916","doi":"https://doi.org/10.48550/arxiv.2602.18825"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.18825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2602.18825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126733415","display_name":"Nicholas Kuhn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuhn, Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010580917","display_name":"Arvid Weyrauch","orcid":"https://orcid.org/0000-0002-2684-0927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weyrauch, Arvid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123432398","display_name":"Lars Helge Heyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heyen, Lars","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030034618","display_name":"Achim Streit","orcid":"https://orcid.org/0000-0002-5065-469X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Streit, Achim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067996051","display_name":"Markus G\u00f6tz","orcid":"https://orcid.org/0000-0002-2233-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00f6tz, Markus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024295845","display_name":"Charlotte Debus","orcid":"https://orcid.org/0000-0002-7156-2022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debus, Charlotte","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.26969999074935913,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.26969999074935913,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.125900000333786,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11129999905824661,"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/lottery","display_name":"Lottery","score":0.7005000114440918},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6880999803543091},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6467000246047974},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5810999870300293},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45080000162124634},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.3806999921798706}],"concepts":[{"id":"https://openalex.org/C2777340749","wikidata":"https://www.wikidata.org/wiki/Q6684955","display_name":"Lottery","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759999990463257},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5928999781608582},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.18825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2602.18825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bayesian":[0,103,116],"neural":[1,19],"networks":[2,52],"(BNNs)":[3],"are":[4,150],"a":[5,102,124],"useful":[6],"tool":[7],"for":[8,57],"uncertainty":[9],"quantification,":[10],"but":[11],"require":[12],"substantially":[13],"more":[14],"computational":[15,58],"resources":[16,59],"than":[17],"conventional":[18],"networks.":[20],"For":[21],"non-Bayesian":[22],"networks,":[23],"the":[24,30,39,46,55,68,78,89,98,112,137,163],"Lottery":[25,131],"Ticket":[26],"Hypothesis":[27],"(LTH)":[28],"posits":[29],"existence":[31,66],"of":[32,67,80,115,145,153],"sparse":[33,51,72,81],"subnetworks":[34,73],"that":[35,136,179],"can":[36,53],"train":[37],"to":[38,101,188],"same":[40],"or":[41],"even":[42],"surpassing":[43,148],"accuracy":[44,149],"as":[45],"original":[47],"dense":[48],"network.":[49],"Such":[50],"lower":[54],"demand":[56],"at":[60,158],"inference,":[61],"and":[62,70,84,119,142,147,185],"during":[63],"training.":[64],"The":[65],"LTH":[69,99,138],"corresponding":[71],"in":[74,140],"BNNs":[75,128],"could":[76],"motivate":[77],"development":[79],"training":[82,91],"algorithms":[83],"provide":[85],"valuable":[86],"insights":[87],"into":[88],"underlying":[90],"process.":[92],"Towards":[93],"this":[94],"end,":[95],"we":[96],"translate":[97],"experiments":[100],"setting":[104],"using":[105],"common":[106],"computer":[107],"vision":[108],"models.":[109],"We":[110,133],"investigate":[111],"defining":[113],"characteristics":[114],"lottery":[117],"tickets,":[118],"extend":[120],"our":[121,176],"study":[122],"towards":[123],"transplantation":[125],"method":[126],"connecting":[127],"with":[129,156],"deterministic":[130],"Tickets.":[132],"generally":[134],"find":[135],"holds":[139],"BNNs,":[141],"winning":[143],"tickets":[144],"matching":[146],"present":[151],"independent":[152],"model":[154],"size,":[155],"degradation":[157],"very":[159],"high":[160],"sparsities.":[161],"However,":[162],"pruning":[164],"strategy":[165],"should":[166],"rely":[167,181],"primarily":[168],"on":[169,172,182],"magnitude,":[170],"secondly":[171],"standard":[173],"deviation.":[174],"Furthermore,":[175],"results":[177],"demonstrate":[178],"models":[180],"mask":[183],"structure":[184],"weight":[186],"initialization":[187],"varying":[189],"degrees.":[190]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-26T00:00:00"}