{"id":"https://openalex.org/W4417453671","doi":"https://doi.org/10.48550/arxiv.2512.13111","title":"From Overfitting to Reliability: Introducing the Hierarchical Approximate Bayesian Neural Network","display_name":"From Overfitting to Reliability: Introducing the Hierarchical Approximate Bayesian Neural Network","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417453671","doi":"https://doi.org/10.48550/arxiv.2512.13111"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.13111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13111","pdf_url":"https://arxiv.org/pdf/2512.13111","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.13111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109816643","display_name":"Hayk Amirkhanian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amirkhanian, Hayk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031354877","display_name":"Marco F. Huber","orcid":"https://orcid.org/0000-0002-8250-2092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huber, Marco F.","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":true,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6639000177383423,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6639000177383423,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.10339999943971634,"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":0.048700001090765,"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/overfitting","display_name":"Overfitting","score":0.9200999736785889},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6729999780654907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6718999743461609},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5928999781608582},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43880000710487366}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9200999736785889},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6729999780654907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6718999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6327000260353088},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6083999872207642},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43880000710487366},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2750999927520752}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.13111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13111","pdf_url":"https://arxiv.org/pdf/2512.13111","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.13111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13111","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.13111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13111","pdf_url":"https://arxiv.org/pdf/2512.13111","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417453671.pdf","grobid_xml":"https://content.openalex.org/works/W4417453671.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"neural":[3,21],"networks":[4,22],"have":[5],"revolutionized":[6],"various":[7],"domains,":[8],"yet":[9],"challenges":[10,29],"such":[11],"as":[12,61],"hyperparameter":[13],"tuning":[14],"and":[15,73,86,123],"overfitting":[16,122],"remain":[17],"significant":[18],"hurdles.":[19],"Bayesian":[20,50],"offer":[23],"a":[24,53,58,62,146],"framework":[25],"to":[26,68,91,108],"address":[27],"these":[28],"by":[30],"incorporating":[31],"uncertainty":[32,126],"directly":[33],"into":[34],"the":[35,65,71,76,83,92,95,109],"model,":[36],"yielding":[37],"more":[38],"reliable":[39,125],"predictions,":[40],"particularly":[41,128],"for":[42,82,129,149],"out-of-distribution":[43,130],"data.":[44],"This":[45],"paper":[46],"presents":[47],"Hierarchical":[48],"Approximate":[49],"Neural":[51],"Network,":[52],"novel":[54],"approach":[55],"that":[56,135],"uses":[57],"Gaussian-inverse-Wishart":[59],"distribution":[60,85],"hyperprior":[63],"of":[64,75,94,97,111,121],"network's":[66],"weights":[67],"increase":[69],"both":[70],"robustness":[72],"performance":[74],"model.":[77],"We":[78],"provide":[79],"analytical":[80],"representations":[81],"predictive":[84],"weight":[87],"posterior,":[88],"which":[89],"amount":[90],"calculation":[93],"parameters":[96],"Student's":[98],"t-distributions":[99],"in":[100,152],"closed":[101],"form":[102],"with":[103,106],"linear":[104],"complexity":[105],"respect":[107],"number":[110],"weights.":[112],"Our":[113],"method":[114],"demonstrates":[115],"robust":[116],"performance,":[117],"effectively":[118],"addressing":[119],"issues":[120],"providing":[124],"estimates,":[127],"tasks.":[131],"Experimental":[132],"results":[133],"indicate":[134],"HABNN":[136],"not":[137],"only":[138],"matches":[139],"but":[140],"often":[141],"outperforms":[142],"state-of-the-art":[143],"models,":[144],"suggesting":[145],"promising":[147],"direction":[148],"future":[150],"applications":[151],"safety-critical":[153],"environments.":[154]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-12-17T00:00:00"}