{"id":"https://openalex.org/W4414359575","doi":"https://doi.org/10.24963/ijcai.2025/721","title":"AdaR: An Adaptive Gradient Method with Cyclical Restarting of Moment Estimations","display_name":"AdaR: An Adaptive Gradient Method with Cyclical Restarting of Moment Estimations","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359575","doi":"https://doi.org/10.24963/ijcai.2025/721"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/721","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120142981","display_name":"Yiwen Wang","orcid":"https://orcid.org/0009-0002-2234-8799"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangchuan Wang","raw_affiliation_strings":["Beijing Wuzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Wuzi University","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015519978","display_name":"Lianhong Ding","orcid":"https://orcid.org/0000-0002-0843-2065"},"institutions":[{"id":"https://openalex.org/I176432857","display_name":"Beijing Wuzi University","ror":"https://ror.org/00bd1d647","country_code":"CN","type":"education","lineage":["https://openalex.org/I176432857"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianhong Ding","raw_affiliation_strings":["Beijing Wuzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Wuzi University","institution_ids":["https://openalex.org/I176432857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483396","display_name":"Peng Shi","orcid":"https://orcid.org/0000-0002-5349-6383"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Shi","raw_affiliation_strings":["University of Science and Technology Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"6478","last_page":"6486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9771999716758728,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9771999716758728,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9602000117301941,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.8859999775886536},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6432999968528748},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5252000093460083},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.42669999599456787},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4138999879360199},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.3481999933719635},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.8859999775886536},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5408999919891357},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3822999894618988},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2780033567","wikidata":"https://www.wikidata.org/wiki/Q6823720","display_name":"Method of moments (probability theory)","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C92951342","wikidata":"https://www.wikidata.org/wiki/Q1411166","display_name":"Orthonormality","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C61062188","wikidata":"https://www.wikidata.org/wiki/Q835065","display_name":"Second moment of area","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C135692309","wikidata":"https://www.wikidata.org/wiki/Q111124","display_name":"Square (algebra)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/721","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Adaptive":[0],"gradient":[1,64],"methods,":[2],"primarily":[3],"based":[4],"on":[5,169],"Adam,":[6],"are":[7],"prevalent":[8],"in":[9,35,111,128],"training":[10,74],"neural":[11],"networks,":[12],"adjusting":[13],"step":[14,160],"sizes":[15],"via":[16,66],"exponentially":[17],"decaying":[18],"averages":[19],"of":[20,83,97],"gradients":[21,34,40],"and":[22,89,107,146,158,172,179],"squared":[23],"gradients.":[24],"Adam":[25],"assigns":[26],"small":[27],"weights":[28],"to":[29,123],"distant":[30,137],"gradients,":[31,138,152],"termed":[32],"long-tail":[33],"this":[36,51],"paper.":[37],"However,":[38],"these":[39],"persistently":[41],"influence":[42],"update":[43],"behavior,":[44],"potentially":[45],"degrading":[46],"generalization":[47,178],"performance.":[48],"To":[49],"address":[50],"issue,":[52],"we":[53],"incorporate":[54],"a":[55,73],"restart":[56,133],"mechanism":[57,134],"into":[58,76],"moment":[59,68,84,92,141],"estimations,":[60],"proposing":[61],"AdaR":[62,71,164],"(ADAptive":[63],"methods":[65],"Restarting":[67],"estimations).":[69],"Specifically,":[70],"divides":[72],"epoch":[75],"fixed-iteration":[77],"intervals,":[78],"alternating":[79],"between":[80],"two":[81],"sets":[82],"estimations":[85,93,142],"for":[86,126,143],"parameter":[87,144],"updates":[88,105,127],"discarding":[90],"prior":[91],"at":[94,120],"the":[95,112,116,121,129,153],"beginning":[96],"each":[98,101],"interval.":[99,131],"Within":[100],"interval,":[102,114],"one":[103],"set":[104],"parameters":[106],"will":[108],"be":[109],"discarded":[110],"subsequent":[113,130],"while":[115],"other":[117],"is":[118],"reset":[119],"midpoint":[122],"estimate":[124],"moments":[125],"The":[132],"cyclically":[135],"discards":[136],"initiates":[139],"fresh":[140],"updates,":[145],"stabilizes":[147],"training.":[148],"By":[149],"prioritizing":[150],"recent":[151],"method":[154],"increases":[155],"estimation":[156],"accuracy":[157],"enhances":[159],"size":[161],"adjustment.":[162],"Empirically,":[163],"outperforms":[165],"state-of-the-art":[166],"optimization":[167],"algorithms":[168],"image":[170],"classification":[171],"language":[173],"modeling":[174],"tasks,":[175],"demonstrating":[176],"superior":[177],"faster":[180],"convergence.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}