{"id":"https://openalex.org/W7154107205","doi":"https://doi.org/10.48550/arxiv.2604.09437","title":"AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning","display_name":"AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154107205","doi":"https://doi.org/10.48550/arxiv.2604.09437"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09437","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09437","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071973954","display_name":"Ioannis Tsingalis","orcid":"https://orcid.org/0000-0003-2590-325X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsingalis, Ioannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065184406","display_name":"Constantine Kotropoulos","orcid":"https://orcid.org/0000-0001-9939-7930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kotropoulos, Constantine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000665137","display_name":"Corentin Briat","orcid":"https://orcid.org/0000-0003-1822-2683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Briat, Corentin","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8485999703407288,"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":0.8485999703407288,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.08879999816417694,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.011699999682605267,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.7843000292778015},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6644999980926514},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.54830002784729},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5267000198364258},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44589999318122864},{"id":"https://openalex.org/keywords/proximal-gradient-methods-for-learning","display_name":"Proximal gradient methods for learning","score":0.34950000047683716},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3384000062942505}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.7843000292778015},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6644999980926514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5361999869346619},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699000120162964},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4677000045776367},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C79248915","wikidata":"https://www.wikidata.org/wiki/Q17086776","display_name":"Proximal gradient methods for learning","level":5,"score":0.34950000047683716},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32120001316070557},{"id":"https://openalex.org/C65559279","wikidata":"https://www.wikidata.org/wiki/Q16667694","display_name":"Cubic function","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C91429207","wikidata":"https://www.wikidata.org/wiki/Q5192245","display_name":"Cubic form","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C64485984","wikidata":"https://www.wikidata.org/wiki/Q4044484","display_name":"Monotone cubic interpolation","level":5,"score":0.275299996137619},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09437","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09437","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09437","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09437","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,"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"},"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":{"A":[0],"novel":[1],"regularization":[2,141],"technique,":[3],"AdaCubic,":[4],"is":[5,19,99,117,134],"proposed":[6],"that":[7,27,56,80,94],"adapts":[8],"the":[9,12,30,33,47,59,135],"weight":[10,31],"of":[11,17,32,105],"cubic":[13,25,34,38,140],"term.":[14],"The":[15],"heart":[16],"AdaCubic":[18,57,81,98,121,133],"an":[20,122],"auxiliary":[21],"optimization":[22],"problem":[23],"with":[24,85,101],"constraints":[26],"dynamically":[28],"adjusts":[29],"term":[35],"in":[36,69,113,142],"Newton's":[37],"regularized":[39,61],"method.":[40],"We":[41,54],"use":[42],"Hutchinson's":[43],"method":[44],"to":[45,138],"approximate":[46],"Hessian":[48],"matrix,":[49],"thereby":[50],"reducing":[51],"computational":[52],"cost.":[53],"demonstrate":[55,79],"inherits":[58],"cubically":[60],"Newton":[62],"method's":[63],"local":[64],"convergence":[65],"guarantees.":[66],"Our":[67],"experiments":[68],"Computer":[70],"Vision,":[71],"Natural":[72],"Language":[73],"Processing,":[74],"and":[75,127],"Signal":[76],"Processing":[77],"tasks":[78],"outperforms":[82],"or":[83],"competes":[84],"several":[86],"widely":[87],"used":[88],"optimizers.":[89],"Unlike":[90],"other":[91],"adaptive":[92],"algorithms":[93],"require":[95],"hyperparameter":[96],"fine-tuning,":[97],"evaluated":[100],"a":[102,109],"fixed":[103],"set":[104],"hyperparameters,":[106],"rendering":[107],"it":[108],"highly":[110],"attractive":[111,123],"optimizer":[112,137],"settings":[114],"where":[115],"fine-tuning":[116],"infeasible.":[118],"This":[119],"makes":[120],"option":[124],"for":[125],"researchers":[126],"practitioners":[128],"alike.":[129],"To":[130],"our":[131],"knowledge,":[132],"first":[136],"leverage":[139],"scalable":[143],"deep":[144],"learning":[145],"applications.":[146]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-14T00:00:00"}