{"id":"https://openalex.org/W4414802004","doi":"https://doi.org/10.48550/arxiv.2507.12142","title":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","display_name":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4414802004","doi":"https://doi.org/10.48550/arxiv.2507.12142"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.12142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12142","pdf_url":"https://arxiv.org/pdf/2507.12142","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039381833","display_name":"Vladimir Igorevich Bogachev","orcid":"https://orcid.org/0000-0001-5249-2965","observed_orcids":["https://orcid.org/0000-0001-5249-2965"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogachev, Vladimir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120534259","display_name":"Vladimir Igorevich Aletov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aletov, Vladimir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119711056","display_name":"Alexander Molozhavenko","orcid":"https://orcid.org/0009-0007-3908-4079","observed_orcids":["https://orcid.org/0009-0007-3908-4079"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Molozhavenko, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099230373","display_name":"Denis Bobkov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bobkov, Denis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111232092","display_name":"Vera Soboleva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soboleva, Vera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051275168","display_name":"Aibek Alanov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alanov, Aibek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050283603","display_name":"Maxim Rakhuba","orcid":"https://orcid.org/0000-0001-7606-7322","observed_orcids":["https://orcid.org/0000-0001-7606-7322"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rakhuba, Maxim","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":1,"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":0.6089000105857849,"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":0.6089000105857849,"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":0.3012999892234802,"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/T10028","display_name":"Topic Modeling","score":0.017100000753998756,"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/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8899999856948853},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.8960000276565552},{"id":"https://openalex.org/keywords/riemannian-optimization","display_name":"Riemannian optimization","score":0.9850000143051147},{"id":"https://openalex.org/keywords/muon-optimizer","display_name":"Muon optimizer","score":0.9169999957084656},{"id":"https://openalex.org/keywords/riemannian-gradient","display_name":"Riemannian gradient","score":0.7350000143051147},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.968999981880188},{"id":"https://openalex.org/keywords/automatic-differentiation","display_name":"automatic differentiation","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5260999798774719},{"id":"https://openalex.org/C2779593128","wikidata":"https://www.wikidata.org/wiki/Q632814","display_name":"Riemannian manifold","level":2,"score":0.5108000040054321},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.4844000041484833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3626999855041504},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.12142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12142","pdf_url":"https://arxiv.org/pdf/2507.12142","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,"listed_in":[],"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.2507.12142","doi":"https://doi.org/10.48550/arxiv.2507.12142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12142","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12142","pdf_url":"https://arxiv.org/pdf/2507.12142","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166695444","https://openalex.org/W7168058029","https://openalex.org/W7220943988","https://openalex.org/W7212902800","https://openalex.org/W7214751144","https://openalex.org/W7207708772","https://openalex.org/W4402619439","https://openalex.org/W4391591020","https://openalex.org/W4404314198","https://openalex.org/W4404307070"],"abstract_inverted_index":{"This":[0,25],"work":[1],"presents":[2],"a":[3,49,68],"novel,":[4],"fully":[5],"Riemannian":[6,51,69],"framework":[7,37],"for":[8],"Low-Rank":[9],"Adaptation":[10],"(LoRA)":[11],"that":[12,58,83,112],"geometrically":[13],"treats":[14],"low-rank":[15],"adapters":[16],"by":[17],"optimizing":[18],"them":[19],"directly":[20],"on":[21,53,104],"the":[22,28,54,60],"fixed-rank":[23,55],"manifold.":[24],"formulation":[26],"eliminates":[27],"parametrization":[29],"ambiguity":[30],"present":[31],"in":[32,97,120],"standard":[33,129],"Euclidean":[34],"optimizers.":[35],"Our":[36],"integrates":[38],"three":[39],"key":[40],"components":[41],"to":[42,87,94],"achieve":[43],"this:":[44],"(1)":[45],"we":[46,66,75],"derive":[47],"Riemannion,":[48],"new":[50],"optimizer":[52],"matrix":[56],"manifold":[57],"generalizes":[59],"recently":[61],"proposed":[62],"Muon":[63],"optimizer;":[64],"(2)":[65],"develop":[67],"gradient-informed":[70],"LoRA":[71,130],"initialization,":[72],"and":[73,107,117,123,131],"(3)":[74],"provide":[76],"an":[77],"efficient":[78],"implementation":[79],"without":[80],"prominent":[81],"overhead":[82],"uses":[84],"automatic":[85],"differentiation":[86],"compute":[88],"arising":[89],"geometric":[90],"operations":[91],"while":[92],"adhering":[93],"best":[95],"practices":[96],"numerical":[98],"linear":[99],"algebra.":[100],"Comprehensive":[101],"experimental":[102],"results":[103],"both":[105,128],"LLM":[106],"diffusion":[108],"model":[109],"architectures":[110],"demonstrate":[111],"our":[113],"approach":[114],"yields":[115],"consistent":[116],"noticeable":[118],"improvements":[119],"convergence":[121],"speed":[122],"final":[124],"task":[125],"performance":[126],"over":[127],"its":[132],"state-of-the-art":[133],"modifications.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}