{"id":"https://openalex.org/W7166672348","doi":"https://doi.org/10.48550/arxiv.2606.29184","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","display_name":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166672348","doi":"https://doi.org/10.48550/arxiv.2606.29184"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29184","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":null,"license_id":null,"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.2606.29184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139633309","display_name":"Zhibin Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Zhibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139640533","display_name":"Yuhong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808531","display_name":"Jiahong Fu","orcid":"https://orcid.org/0009-0008-8514-5298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jiahong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065256379","display_name":"Zongsheng Yue","orcid":"https://orcid.org/0000-0002-9178-671X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Zongsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139691619","display_name":"Bo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073136550","display_name":"Zhewei Xu","orcid":"https://orcid.org/0000-0003-4718-6175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zongben","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4296000003814697,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4296000003814697,"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":0.14319999516010284,"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":0.05620000138878822,"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/generalization","display_name":"Generalization","score":0.6787999868392944},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6779999732971191},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6629999876022339},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6571000218391418},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5236999988555908},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.36079999804496765},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6787999868392944},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6779999732971191},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6629999876022339},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6571000218391418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467999815940857},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29184","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29184","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":null,"license_id":null,"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":{"While":[0],"Low-rank":[1],"adaptation":[2,47,66,92],"(LoRA)":[3],"enables":[4],"highly":[5],"efficient":[6],"fine-tuning":[7],"by":[8,42,94,149],"constraining":[9],"task-specific":[10],"updates":[11],"to":[12,196],"fixed":[13,55],"low-rank":[14],"subspaces,":[15],"this":[16,69],"rigid":[17],"design":[18],"limits":[19],"representational":[20],"flexibility":[21],"and":[22,28,192,199],"often":[23],"results":[24],"in":[25,32,107],"overconfident":[26],"predictions":[27],"miscalibrated":[29],"uncertainty,":[30],"especially":[31],"low-data":[33],"regimes.":[34],"Recent":[35],"Bayesian":[36,75,111,201],"LoRA":[37,198,202],"variants":[38],"improve":[39],"uncertainty":[40,193],"estimation":[41],"modeling":[43,125],"posterior":[44],"distributions":[45],"over":[46],"parameters.":[48],"However,":[49],"these":[50],"approaches":[51],"typically":[52],"rely":[53],"on":[54,141,179],"or":[56],"heuristically":[57],"determined":[58],"ranks,":[59],"overlooking":[60],"the":[61,124,135,142,150,155,169],"inherently":[62],"context-dependent":[63,98],"nature":[64],"of":[65,100,138],"capacity.":[67],"In":[68],"paper,":[70],"we":[71,127],"propose":[72],"BaRA,":[73],"a":[74,96,129],"Adaptive":[76],"Rank":[77],"Allocation":[78],"framework":[79],"for":[80],"parameter-efficient":[81],"fine-tuning.":[82],"Drawing":[83],"inspiration":[84],"from":[85],"probabilistic":[86],"topic":[87],"models,":[88],"BaRA":[89,139,186],"dynamically":[90],"allocates":[91],"capacity":[93,116],"activating":[95],"sparse,":[97],"subset":[99],"disentangled":[101],"latent":[102],"factors,":[103],"enabling":[104],"instance-wise":[105],"variation":[106],"effective":[108,145,170],"rank.":[109],"This":[110,159],"formulation":[112],"provides":[113],"principled,":[114],"data-driven":[115],"control,":[117],"mitigating":[118],"over-parameterization":[119],"while":[120,173],"preserving":[121,174],"expressiveness.":[122,176],"Beyond":[123],"contribution,":[126],"provide":[128],"complexity-theoretic":[130],"generalization":[131,136],"analysis":[132],"showing":[133],"that":[134,185],"gap":[137],"depends":[140],"learned":[143],"joint":[144],"rank":[146,157,165],"$\\bar{s}_{\u03a6,\u03b8}$":[147],"induced":[148],"global-local":[151],"gate,":[152],"rather":[153],"than":[154],"maximum":[156],"$r$.":[158],"result":[160],"explains":[161],"why":[162],"sparse":[163],"adaptive":[164],"allocation":[166],"can":[167],"reduce":[168],"hypothesis":[171],"complexity":[172],"input-dependent":[175],"Extensive":[177],"experiments":[178],"diverse":[180],"natural":[181],"language":[182],"benchmarks":[183],"demonstrate":[184],"consistently":[187],"improves":[188],"predictive":[189],"performance,":[190],"robustness,":[191],"calibration":[194],"compared":[195],"standard":[197],"existing":[200],"variants.":[203]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}