{"id":"https://openalex.org/W4416033974","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1143","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","display_name":"Riemannian Optimization for LoRA on the Stiefel Manifold","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033974","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1143"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1143","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1143.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"JuneYoung Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"JuneYoung Park","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058414558","display_name":"Minjae Kang","orcid":"https://orcid.org/0009-0008-7847-9687"},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Minjae Kang","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022594999","display_name":"Seongbae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Seongbae Lee","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haegang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Haegang Lee","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008532313","display_name":"Seongwan Kim","orcid":"https://orcid.org/0000-0002-0962-9812"},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Seongwan Kim","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331202","display_name":"Jae-Ho Lee","orcid":"https://orcid.org/0000-0002-5676-8612"},"institutions":[{"id":"https://openalex.org/I4210127161","display_name":"Observatorio de Prospectiva Tecnol\u00f3gica Industrial","ror":"https://ror.org/03f6cng42","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210127161"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jaeho Lee","raw_affiliation_strings":["Opt-AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opt-AI Inc","institution_ids":["https://openalex.org/I4210127161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3620508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20971","last_page":"20985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12417","display_name":"Morphological variations and asymmetry","score":0.2329999953508377,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12417","display_name":"Morphological variations and asymmetry","score":0.2329999953508377,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.21529999375343323,"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/T12261","display_name":"Statistical Mechanics and Entropy","score":0.06419999897480011,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stiefel-manifold","display_name":"Stiefel manifold","score":0.5938000082969666},{"id":"https://openalex.org/keywords/riemannian-manifold","display_name":"Riemannian manifold","score":0.4327000081539154},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/statistical-manifold","display_name":"Statistical manifold","score":0.3434000015258789},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3285999894142151},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.3012000024318695},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.290800005197525}],"concepts":[{"id":"https://openalex.org/C612670","wikidata":"https://www.wikidata.org/wiki/Q7616373","display_name":"Stiefel manifold","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5070000290870667},{"id":"https://openalex.org/C2779593128","wikidata":"https://www.wikidata.org/wiki/Q632814","display_name":"Riemannian manifold","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C169391604","wikidata":"https://www.wikidata.org/wiki/Q7604402","display_name":"Statistical manifold","level":5,"score":0.3434000015258789},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C121705324","wikidata":"https://www.wikidata.org/wiki/Q1510587","display_name":"Pseudo-Riemannian manifold","level":4,"score":0.28619998693466187},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.27559998631477356},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1143","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1143","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033974.pdf","grobid_xml":"https://content.openalex.org/works/W4416033974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"powerful,":[1],"large":[2],"language":[3],"models":[4],"(LLMs)":[5],"present":[6],"significant":[7],"fine-tuning":[8,14],"challenges":[9],"due":[10],"to":[11,92],"their":[12],"size.Parameter-efficient":[13],"(PEFT)":[15],"methods":[16],"like":[17],"LoRA":[18,82],"provide":[19],"solutions,":[20],"yet":[21],"suffer":[22],"from":[23],"critical":[24],"optimizer":[25,74],"inefficiencies;":[26],"notably":[27],"basis":[28],"redundancy":[29],"in":[30],"LoRA's":[31,94],"B":[32,46],"matrix":[33,47],"when":[34],"using":[35],"AdamW,":[36],"which":[37],"fundamentally":[38],"limits":[39],"performance.We":[40],"address":[41],"this":[42],"by":[43],"optimizing":[44],"the":[45,49,90],"on":[48],"Stiefel":[50,73],"manifold,":[51],"imposing":[52],"explicit":[53],"orthogonality":[54,59],"constraints":[55,88],"that":[56,86],"achieve":[57],"near-perfect":[58],"and":[60,70,83],"full":[61,95],"effective":[62,98],"rank.This":[63],"geometric":[64,87],"approach":[65],"dramatically":[66],"enhances":[67],"parameter":[68],"efficiency":[69],"representational":[71],"capacity.Our":[72],"consistently":[75],"outperforms":[76],"AdamW":[77],"across":[78],"benchmarks":[79],"with":[80],"both":[81],"DoRA,":[84],"demonstrating":[85],"are":[89],"key":[91],"unlocking":[93],"potential":[96],"for":[97],"LLM":[99],"finetuning.":[100]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}