{"id":"https://openalex.org/W4415715624","doi":"https://doi.org/10.1088/2632-2153/ae19cc","title":"Dynamic learning rate decay for stochastic variational inference","display_name":"Dynamic learning rate decay for stochastic variational inference","publication_year":2025,"publication_date":"2025-10-30","ids":{"openalex":"https://openalex.org/W4415715624","doi":"https://doi.org/10.1088/2632-2153/ae19cc"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ae19cc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae19cc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ae19cc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042594342","display_name":"Maximilian Dinkel","orcid":"https://orcid.org/0009-0003-2908-2951"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maximilian Dinkel","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0003-2908-2951","affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007221923","display_name":"Gil Robalo Rei","orcid":"https://orcid.org/0000-0002-6336-6718"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gil Robalo Rei","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6336-6718","affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053323760","display_name":"Wolfgang A. Wall","orcid":"https://orcid.org/0000-0001-7419-3384"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang A Wall","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Munich, Germany","Munich Data Science Institute, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7419-3384","affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Munich Data Science Institute, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042594342"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15825635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"4","first_page":"045041","last_page":"045041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.5349000096321106,"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":0.5349000096321106,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.26489999890327454,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0674000009894371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4975999891757965},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.4187999963760376},{"id":"https://openalex.org/keywords/wake-sleep-algorithm","display_name":"Wake-sleep algorithm","score":0.41260001063346863},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3862000107765198},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.38100001215934753},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.35740000009536743},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.3538999855518341}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47040000557899475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C17061570","wikidata":"https://www.wikidata.org/wiki/Q7960888","display_name":"Wake-sleep algorithm","level":4,"score":0.41260001063346863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40529999136924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40059998631477356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/ae19cc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae19cc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bb3d2569f34a473b9c3ace9a14dec36d","is_oa":true,"landing_page_url":"https://doaj.org/article/bb3d2569f34a473b9c3ace9a14dec36d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 6, Iss 4, p 045041 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ae19cc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae19cc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1709901070","display_name":"Unlocking vital mysteries in respiratory biomechanics","funder_award_id":"101021526","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1970789124","https://openalex.org/W1979744342","https://openalex.org/W1994616650","https://openalex.org/W2045246746","https://openalex.org/W2102661631","https://openalex.org/W2142819099","https://openalex.org/W2225156818","https://openalex.org/W4401119820"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Like":[1],"many":[2],"optimization":[3,25,216],"algorithms,":[4],"stochastic":[5],"variational":[6,97,168,186],"inference":[7],"is":[8,21,47,93,135,199],"sensitive":[9],"to":[10,57,59,117,157,175,188,218],"the":[11,14,18,24,31,40,44,50,78,83,89,96,103,110,122,126,145,148,159,164,167,177,182,185,190,212,215,219],"choice":[12],"of":[13,85,147,166,179,184,214],"learning":[15,19,45,63,79,91,107,111,127,160,191,220,234],"rate.":[16,192],"If":[17],"rate":[20,46,64,80,92,108,112,128,161,221,235],"too":[22,48,94],"small,":[23],"process":[26],"may":[27,52],"be":[28,114,130,227],"slow,":[29],"and":[30,198,222],"algorithm":[32,51],"might":[33,99],"get":[34],"stuck":[35],"in":[36,132,204,229],"local":[37],"optima.":[38],"On":[39],"other":[41,232],"hand,":[42],"if":[43,88],"large,":[49,95],"oscillate":[53,101],"or":[54,71],"diverge,":[55],"failing":[56],"converge":[58],"a":[60,138,155],"solution.":[61,105],"Adaptive":[62],"methods":[65],"such":[66],"as":[67],"Adam,":[68],"AdaMax,":[69],"Adagrad,":[70],"root":[72],"mean":[73],"square":[74],"propagation":[75],"automatically":[76],"adjust":[77],"based":[81,162],"on":[82,163],"history":[84,165],"gradients.":[86],"Nevertheless,":[87],"base":[90],"parameters":[98,187],"still":[100],"around":[102],"optimal":[104],"With":[106],"schedules,":[109],"can":[113,142,225],"reduced":[115],"gradually":[116],"mitigate":[118],"this":[119,151],"problem.":[120],"However,":[121],"amount":[123,178],"at":[124],"which":[125,141],"should":[129],"decreased":[131],"each":[133],"iteration":[134],"not":[136],"known":[137],"priori":[139],",":[140],"significantly":[143],"impact":[144],"performance":[146,217],"optimization.":[149],"In":[150],"work,":[152],"we":[153],"propose":[154],"method":[156,210],"decay":[158],"parameters.":[169],"We":[170,202],"use":[171],"an":[172],"empirical":[173],"measure":[174],"quantify":[176],"oscillations":[180],"against":[181],"progress":[183],"adapt":[189],"The":[193],"approach":[194],"requires":[195],"little":[196],"memory":[197],"computationally":[200],"efficient.":[201],"demonstrate":[203],"various":[205],"numerical":[206],"examples":[207],"that":[208,223],"our":[209],"reduces":[211],"sensitivity":[213],"it":[224],"also":[226],"used":[228],"combination":[230],"with":[231],"adaptive":[233],"methods.":[236]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-31T00:00:00"}