{"id":"https://openalex.org/W3174794150","doi":"https://doi.org/10.1109/icassp43922.2022.9746839","title":"Demon: Improved Neural Network Training With Momentum Decay","display_name":"Demon: Improved Neural Network Training With Momentum Decay","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3174794150","doi":"https://doi.org/10.1109/icassp43922.2022.9746839","mag":"3174794150"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746839","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101650717","display_name":"John Chen","orcid":"https://orcid.org/0000-0002-9443-4795"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Chen","raw_affiliation_strings":["Rice University,Houston,Texas","Rice University, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University,Houston,Texas","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014694879","display_name":"C. Wolfe","orcid":"https://orcid.org/0000-0003-3954-1229"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cameron Wolfe","raw_affiliation_strings":["Rice University,Houston,Texas","Rice University, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University,Houston,Texas","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730692","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0001-5787-2705"},"institutions":[{"id":"https://openalex.org/I4210159031","display_name":"The University of Texas Health Science Center","ror":"https://ror.org/05cwbxa29","country_code":"US","type":"education","lineage":["https://openalex.org/I4210159031"]},{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Li","raw_affiliation_strings":["UTHealth,Houston,Texas","UTHealth, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTHealth,Houston,Texas","institution_ids":["https://openalex.org/I4210159031","https://openalex.org/I919571938"]},{"raw_affiliation_string":"UTHealth, Houston, Texas","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024280658","display_name":"Anastasios Kyrillidis","orcid":"https://orcid.org/0000-0003-1954-8730"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasios Kyrillidis","raw_affiliation_strings":["Rice University,Houston,Texas","Rice University, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University,Houston,Texas","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5718,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89153556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3958","last_page":"3962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973000288009644,"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":0.9972000122070312,"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/demon","display_name":"Demon","score":0.7135115265846252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940023899078369},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.6606713533401489},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6498883366584778},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.595558226108551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5354127883911133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5334109663963318},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.528141975402832},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.48900139331817627},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11552491784095764}],"concepts":[{"id":"https://openalex.org/C2779227343","wikidata":"https://www.wikidata.org/wiki/Q5256190","display_name":"Demon","level":2,"score":0.7135115265846252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940023899078369},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6606713533401489},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6498883366584778},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.595558226108551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5354127883911133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5334109663963318},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.528141975402832},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.48900139331817627},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11552491784095764},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746839","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":116,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W104184427","https://openalex.org/W131533222","https://openalex.org/W639708223","https://openalex.org/W806995027","https://openalex.org/W1522301498","https://openalex.org/W1599016936","https://openalex.org/W1686810756","https://openalex.org/W1959608418","https://openalex.org/W2064675550","https://openalex.org/W2097460613","https://openalex.org/W2125389028","https://openalex.org/W2127447444","https://openalex.org/W2130158090","https://openalex.org/W2137731592","https://openalex.org/W2146502635","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2251939518","https://openalex.org/W2259558022","https://openalex.org/W2336650964","https://openalex.org/W2396767181","https://openalex.org/W2402144811","https://openalex.org/W2518108298","https://openalex.org/W2523246573","https://openalex.org/W2540893630","https://openalex.org/W2549139847","https://openalex.org/W2552959509","https://openalex.org/W2565639579","https://openalex.org/W2612445135","https://openalex.org/W2625885504","https://openalex.org/W2752782242","https://openalex.org/W2766164908","https://openalex.org/W2768282280","https://openalex.org/W2785523195","https://openalex.org/W2795247881","https://openalex.org/W2806120502","https://openalex.org/W2807915830","https://openalex.org/W2808042107","https://openalex.org/W2848500096","https://openalex.org/W2896101215","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2901831961","https://openalex.org/W2923014074","https://openalex.org/W2953384591","https://openalex.org/W2959300817","https://openalex.org/W2962739925","https://openalex.org/W2962795635","https://openalex.org/W2962861703","https://openalex.org/W2963208657","https://openalex.org/W2963263347","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963430672","https://openalex.org/W2963446712","https://openalex.org/W2963495494","https://openalex.org/W2963684088","https://openalex.org/W2963698657","https://openalex.org/W2963703618","https://openalex.org/W2963748441","https://openalex.org/W2963792515","https://openalex.org/W2963846996","https://openalex.org/W2963858717","https://openalex.org/W2964102336","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2970623506","https://openalex.org/W2970990876","https://openalex.org/W2971034910","https://openalex.org/W2978017171","https://openalex.org/W2980149079","https://openalex.org/W2980282514","https://openalex.org/W2982000031","https://openalex.org/W2995782642","https://openalex.org/W3016339201","https://openalex.org/W3030163527","https://openalex.org/W3032929727","https://openalex.org/W3035314311","https://openalex.org/W3092043977","https://openalex.org/W4292779060","https://openalex.org/W4293765466","https://openalex.org/W4297775537","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6680412534","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6685352114","https://openalex.org/W6703420464","https://openalex.org/W6713134421","https://openalex.org/W6725739302","https://openalex.org/W6726497184","https://openalex.org/W6737664043","https://openalex.org/W6739170280","https://openalex.org/W6743731764","https://openalex.org/W6746052068","https://openalex.org/W6747620207","https://openalex.org/W6749646390","https://openalex.org/W6750615492","https://openalex.org/W6755207826","https://openalex.org/W6755246102","https://openalex.org/W6755977018","https://openalex.org/W6756040250","https://openalex.org/W6765775151","https://openalex.org/W6768851824","https://openalex.org/W6775855368","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2245902640","https://openalex.org/W2888133937","https://openalex.org/W3137356709","https://openalex.org/W2027503790","https://openalex.org/W560543696","https://openalex.org/W596113199","https://openalex.org/W3011009274","https://openalex.org/W4242419146","https://openalex.org/W2053642302","https://openalex.org/W4324340252"],"abstract_inverted_index":{"Momentum":[0],"is":[1,113,120,148,169],"a":[2,15,132],"widely":[3],"used":[4],"technique":[5],"for":[6,30],"gradient-based":[7],"optimizers":[8],"in":[9,61,126],"deep":[10],"learning.":[11],"Here,":[12],"we":[13],"propose":[14],"decaying":[16],"momentum":[17,27],"(DEMON)":[18],"hyperparameter":[19],"rule.":[20],"We":[21],"conduct":[22],"large-scale":[23],"empirical":[24],"analysis":[25],"of":[26,49,65,134],"decay":[28,43],"methods":[29],"modern":[31],"neural":[32,124],"network":[33],"optimization":[34],"and":[35,53,58,63,78,101,136,144,156],"compare":[36],"to":[37,116,122,150,164],"the":[38,70,92,106,165],"most":[39],"popular":[40],"learning":[41,73,93,108],"rate":[42,74,94,109],"schedules.":[44],"Across":[45],"28":[46],"relevant":[47],"combinations":[48],"models,":[50,141,143],"epochs,":[51],"datasets,":[52],"optimizers,":[54],"DEMON":[55,81,112,147],"achieves":[56],"Top-1":[57],"Top-3":[59],"performance":[60],"39%":[62],"85%":[64],"cases,":[66],"respectively,":[67],"almost":[68,158],"doubling":[69],"second-placed":[71],"cosine":[72],"schedule":[75],"at":[76],"17%":[77],"60%,":[79],"respectively.":[80],"consistently":[82],"outperforms":[83],"other":[84],"widely-used":[85,107],"schedulers":[86],"including,":[87],"but":[88],"not":[89],"limited":[90],"to,":[91],"step":[95,110],"schedule,":[96,98,100,111],"linear":[97],"OneCycle":[99],"exponential":[102],"schedule.":[103],"Compared":[104],"with":[105],"less":[114],"sensitive":[115],"parameter":[117],"tuning,":[118,155],"which":[119],"critical":[121],"training":[123],"networks":[125],"practice.":[127],"Results":[128],"are":[129],"demonstrated":[130],"across":[131],"variety":[133],"settings":[135],"architectures,":[137],"including":[138],"image":[139],"classification":[140],"generative":[142],"language":[145],"models.":[146],"easy":[149],"implement,":[151],"requires":[152],"no":[153,159],"additional":[154],"incurs":[157],"extra":[160],"computational":[161],"overhead":[162],"compared":[163],"vanilla":[166],"counterparts.":[167],"Code":[168],"readily":[170],"available.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}