{"id":"https://openalex.org/W7212264808","doi":"https://doi.org/10.48550/arxiv.2609.11867","title":"AdamX: Cosine similarity meets gradient descent","display_name":"AdamX: Cosine similarity meets gradient descent","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212264808","doi":"https://doi.org/10.48550/arxiv.2609.11867"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.11867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11867","pdf_url":"https://arxiv.org/pdf/2609.11867","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.11867","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015693527","display_name":"Francisco Caldas","orcid":"https://orcid.org/0000-0001-5090-0216","observed_orcids":["https://orcid.org/0000-0001-5090-0216"]},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Caldas, Francisco","raw_affiliation_strings":["NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120032092","display_name":"Ruben Belo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Belo, Ruben","raw_affiliation_strings":["NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124343413","display_name":"Cl\u00e1udia Soares","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Soares, Cl\u00e1udia","raw_affiliation_strings":["NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA School of Science of Technology Universidade Nova de Lisboa , Caparica , Portugal","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83558840"],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":9.999999747378752e-05,"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/cosine-similarity","display_name":"cosine similarity","score":0.7620000243186951},{"id":"https://openalex.org/keywords/adaptive-learning-rate","display_name":"adaptive learning rate","score":0.6759999990463257},{"id":"https://openalex.org/keywords/first-order-methods","display_name":"first-order methods","score":0.7300000190734863},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"gradient descent","score":0.8989999890327454},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8069999814033508}],"concepts":[{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6177999973297119},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.590499997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5823000073432922},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5554999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5144000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.446399986743927},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.11867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11867","pdf_url":"https://arxiv.org/pdf/2609.11867","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.2609.11867","doi":"https://doi.org/10.48550/arxiv.2609.11867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.11867","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.11867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11867","pdf_url":"https://arxiv.org/pdf/2609.11867","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":[{"id":"https://openalex.org/G2697202684","display_name":null,"funder_award_id":"UID/04516","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320331406","display_name":"NOVA Laboratory for Computer Science and Informatics","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212264808.pdf","grobid_xml":"https://content.openalex.org/works/W7212264808.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4380559103","https://openalex.org/W4417256408"],"related_works":["https://openalex.org/W2998272627","https://openalex.org/W3173690204","https://openalex.org/W4392222230","https://openalex.org/W4287115374","https://openalex.org/W4415797008","https://openalex.org/W4414944394","https://openalex.org/W4416895734","https://openalex.org/W4405955747","https://openalex.org/W4410609437","https://openalex.org/W2952524552"],"abstract_inverted_index":{"We":[0,32],"introduce":[1,34],"AdamX,":[2],"a":[3,35,61,85],"first-order":[4],"optimizer":[5],"that":[6,39,54],"incorporates":[7],"cosine":[8],"similarity":[9],"as":[10],"an":[11],"adaptive":[12],"mechanism":[13],"for":[14],"controlling":[15],"update":[16],"magnitudes.":[17],"The":[18],"proposed":[19],"method":[20],"is":[21,69],"scalable,":[22],"model-agnostic,":[23],"and":[24,66,90],"straightforward":[25],"to":[26,79],"integrate":[27],"into":[28],"existing":[29],"training":[30],"pipelines.":[31],"further":[33],"variance":[36],"rectification":[37],"scheme":[38],"promotes":[40],"smoother":[41],"optimization":[42],"during":[43],"the":[44,74],"early":[45],"stages":[46],"of":[47,63,73,76],"training.":[48],"Overall,":[49],"we":[50],"provide":[51],"empirical":[52],"evidence":[53],"AdamX":[55],"achieves":[56],"competitive":[57],"convergence":[58],"rates":[59],"across":[60],"range":[62],"benchmark":[64],"datasets":[65],"architectures.":[67],"Performance":[68],"evaluated":[70],"in":[71],"terms":[72],"number":[75],"epochs":[77],"required":[78],"reach":[80],"predefined":[81],"performance":[82],"thresholds":[83],"under":[84],"fixed":[86],"hyperparameter":[87],"budget.":[88],"Code":[89],"Experiments":[91],"available":[92],"at:":[93],"https://github.com/FranciscoCaldas/adamX.":[94]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-12T00:00:00"}