{"id":"https://openalex.org/W4408062977","doi":"https://doi.org/10.5220/0013261100003905","title":"Zeroth Order Optimization for Pretraining Language Models","display_name":"Zeroth Order Optimization for Pretraining Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408062977","doi":"https://doi.org/10.5220/0013261100003905"},"language":"en","primary_location":{"id":"doi:10.5220/0013261100003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261100003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013261100003905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116465563","display_name":"Nathan Allaire","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133247","display_name":"Group for Research in Decision Analysis","ror":"https://ror.org/02pkvpx84","country_code":"CA","type":"facility","lineage":["https://openalex.org/I108192572","https://openalex.org/I159129438","https://openalex.org/I4210133247","https://openalex.org/I45683168","https://openalex.org/I49663120","https://openalex.org/I5023651"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nathan Allaire","raw_affiliation_strings":["GERAD, Polytechnique Montr\u00e9al, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"GERAD, Polytechnique Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I45683168","https://openalex.org/I4210133247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114109570","display_name":"Mahsa Ghazvini Nejad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahsa Ghazvini Nejad","raw_affiliation_strings":["Noah\u2019s Ark Lab, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Montr\u00e9al, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022173011","display_name":"S\u00e9bastien Le Digabel","orcid":"https://orcid.org/0000-0003-3148-5090"},"institutions":[{"id":"https://openalex.org/I4210133247","display_name":"Group for Research in Decision Analysis","ror":"https://ror.org/02pkvpx84","country_code":"CA","type":"facility","lineage":["https://openalex.org/I108192572","https://openalex.org/I159129438","https://openalex.org/I4210133247","https://openalex.org/I45683168","https://openalex.org/I49663120","https://openalex.org/I5023651"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Le Digabel","raw_affiliation_strings":["GERAD, Polytechnique Montr\u00e9al, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"GERAD, Polytechnique Montr\u00e9al, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I45683168","https://openalex.org/I4210133247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052855957","display_name":"Vahid Partovi Nia","orcid":"https://orcid.org/0000-0001-6673-4224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahid Partovi Nia","raw_affiliation_strings":["Noah\u2019s Ark Lab, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Montr\u00e9al, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5116465563"],"corresponding_institution_ids":["https://openalex.org/I4210133247","https://openalex.org/I45683168"],"apc_list":null,"apc_paid":null,"fwci":2.7799,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89331224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.36980000138282776,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.36980000138282776,"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/computer-science","display_name":"Computer science","score":0.6964623928070068},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5751224756240845},{"id":"https://openalex.org/keywords/zeroth-law-of-thermodynamics","display_name":"Zeroth law of thermodynamics","score":0.41617852449417114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3364121913909912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3353174924850464},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08330124616622925},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.048499345779418945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964623928070068},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5751224756240845},{"id":"https://openalex.org/C68755742","wikidata":"https://www.wikidata.org/wiki/Q190983","display_name":"Zeroth law of thermodynamics","level":2,"score":0.41617852449417114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3364121913909912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3353174924850464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08330124616622925},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.048499345779418945},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013261100003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261100003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:64441","is_oa":true,"landing_page_url":null,"pdf_url":"https://publications.polymtl.ca/64441/1/2025_Allaire_Zeroth_Order_Optimization_Pretraining_Language.pdf","source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"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":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.5220/0013261100003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261100003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2055832495","https://openalex.org/W4297745082","https://openalex.org/W1993876517","https://openalex.org/W1601218205","https://openalex.org/W2793511430","https://openalex.org/W4210561670","https://openalex.org/W3204019825"],"abstract_inverted_index":{"ABSTRACT:":[0],"The":[1],"physical":[2],"memory":[3,36,97],"for":[4,88,163],"training":[5,56],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"grow":[10],"with":[11,43,50],"the":[12,19,27,30,96,105,108,111,115,122,145,150,155],"model":[13,90],"size,":[14],"and":[15,52,114,131,153],"are":[16,63],"limited":[17],"to":[18,34,66,126],"GPU":[20],"memory.":[21],"In":[22],"particular,":[23],"back-propagation":[24],"that":[25,144],"requires":[26],"computation":[28],"of":[29,77,147,159],"first-order":[31],"derivatives":[32],"adds":[33],"this":[35,68],"overhead.":[37],"Training":[38],"extremely":[39],"large":[40],"language":[41,78,89,129],"models":[42],"memory-efficient":[44],"algorithms":[45],"is":[46,99,149],"still":[47],"a":[48],"challenge":[49],"theoretical":[51],"practical":[53],"implications.":[54],"Back-propagation-free":[55],"algorithms,":[57],"also":[58],"known":[59],"as":[60],"zeroth-order":[61,93],"methods,":[62],"recently":[64],"examined":[65],"address":[67],"challenge.":[69],"Their":[70],"usefulness":[71],"has":[72,84],"been":[73,85],"proven":[74],"in":[75,141],"fine-tuning":[76],"models.":[79,166],"However,":[80],"so":[81],"far,":[82],"there":[83],"no":[86],"study":[87],"pretraining":[91],"using":[92],"optimization,":[94],"where":[95],"constraint":[98],"manifested":[100],"more":[101],"severely.":[102],"We":[103,139],"build":[104],"connection":[106],"between":[107],"second":[109],"order,":[110,113],"first":[112],"zeroth":[116,123,160],"order":[117,124,161],"theoretically.":[118],"Then,":[119],"we":[120],"apply":[121],"optimization":[125],"pre-training":[127,164],"light-weight":[128],"models,":[130],"discuss":[132],"why":[133],"they":[134],"cannot":[135],"be":[136],"readily":[137],"applied.":[138],"show":[140],"p":[142],"articular":[143],"curse":[146],"dimensionality":[148],"main":[151],"obstacle,":[152],"pave":[154],"way":[156],"towards":[157],"modifications":[158],"methods":[162],"such":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}