{"id":"https://openalex.org/W3162168477","doi":"https://doi.org/10.1109/icassp39728.2021.9414419","title":"Improved Step-Size Schedules for Noisy Gradient Methods","display_name":"Improved Step-Size Schedules for Noisy Gradient Methods","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162168477","doi":"https://doi.org/10.1109/icassp39728.2021.9414419","mag":"3162168477"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-295604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027182415","display_name":"Sarit Khirirat","orcid":"https://orcid.org/0000-0003-4473-2011"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Sarit Khirirat","raw_affiliation_strings":["Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968658","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0003-4102-4909"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":["Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054704457","display_name":"Sindri Magn\u00fasson","orcid":"https://orcid.org/0000-0002-6617-8683"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sindri Magnusson","raw_affiliation_strings":["Stockholm University"],"affiliations":[{"raw_affiliation_string":"Stockholm University","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024256519","display_name":"Mikael Johansson","orcid":"https://orcid.org/0000-0002-2237-2580"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Johansson","raw_affiliation_strings":["Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027182415"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71755941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"3655","last_page":"3659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.633212685585022},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5466764569282532},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5435568690299988},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5235587954521179},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48312970995903015},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4781583249568939},{"id":"https://openalex.org/keywords/proximal-gradient-methods","display_name":"Proximal Gradient Methods","score":0.47505781054496765},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4579957127571106},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4478856921195984},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.43493446707725525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29360461235046387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13848081231117249},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.13204225897789001},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.06993627548217773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633212685585022},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5466764569282532},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5435568690299988},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5235587954521179},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48312970995903015},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4781583249568939},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.47505781054496765},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4579957127571106},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4478856921195984},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.43493446707725525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29360461235046387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13848081231117249},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.13204225897789001},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.06993627548217773},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-295604","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-295604","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-127004","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85115103197&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-295604","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-295604","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1513983351","https://openalex.org/W1516903196","https://openalex.org/W1568288633","https://openalex.org/W1992208280","https://openalex.org/W2107438106","https://openalex.org/W2112269233","https://openalex.org/W2149479912","https://openalex.org/W2151695970","https://openalex.org/W2156779765","https://openalex.org/W2617766261","https://openalex.org/W2748196763","https://openalex.org/W2769644379","https://openalex.org/W2785791552","https://openalex.org/W2805997383","https://openalex.org/W2808495300","https://openalex.org/W2963335821","https://openalex.org/W2963664311","https://openalex.org/W2964004663","https://openalex.org/W2964267428","https://openalex.org/W2964725673","https://openalex.org/W3011763294","https://openalex.org/W3013797917","https://openalex.org/W3046889184","https://openalex.org/W3091841423","https://openalex.org/W4297685247","https://openalex.org/W4303683853","https://openalex.org/W6630841318","https://openalex.org/W6676105031","https://openalex.org/W6676963778","https://openalex.org/W6738460352","https://openalex.org/W6746200960","https://openalex.org/W6748019269","https://openalex.org/W6748304459","https://openalex.org/W6752012617","https://openalex.org/W6752838022","https://openalex.org/W6758662331","https://openalex.org/W6774876964","https://openalex.org/W6781729663","https://openalex.org/W6784042051"],"related_works":["https://openalex.org/W2963086517","https://openalex.org/W2564735875","https://openalex.org/W3123504125","https://openalex.org/W3147739796","https://openalex.org/W1983212821","https://openalex.org/W3127841625","https://openalex.org/W2594900731","https://openalex.org/W2811217697","https://openalex.org/W2364728921","https://openalex.org/W2348618647"],"abstract_inverted_index":{"Noise":[0],"is":[1,28,41],"inherited":[2],"in":[3,34,61],"many":[4],"optimization":[5],"methods":[6,13,20,76,113,126,138],"such":[7,19,108],"as":[8,52],"stochastic":[9,66,128],"gradient":[10,16,67,98],"methods,":[11,68],"zeroth-order":[12,125],"and":[14,48,63,127],"compressed":[15],"methods.":[17,99,130],"For":[18],"to":[21,30,45,114],"converge":[22],"toward":[23],"a":[24,93],"global":[25],"optimum,":[26],"it":[27],"intuitive":[29],"use":[31],"large":[32],"step-sizes":[33,51],"the":[35,39,46,50,53,84,140],"initial":[36],"iterations":[37],"when":[38],"noise":[40],"typically":[42],"small":[43],"compared":[44],"algorithm-steps,":[47],"reduce":[49],"algorithm":[54],"progresses.":[55],"This":[56,80],"intuition":[57],"has":[58],"been":[59],"con-firmed":[60],"theory":[62],"practice":[64],"for":[65,74,92],"but":[69],"similar":[70],"results":[71,123],"are":[72],"lacking":[73],"other":[75],"using":[77],"approximate":[78],"gradients.":[79],"paper":[81],"shows":[82,106],"that":[83,107],"diminishing":[85],"step-size":[86,109],"strategies":[87],"can":[88],"indeed":[89],"be":[90],"applied":[91],"broad":[94],"class":[95],"of":[96,136],"noisy":[97],"Unlike":[100],"previous":[101],"works,":[102],"our":[103,122],"analysis":[104],"framework":[105],"schedules":[110],"enable":[111],"these":[112,137],"enjoy":[115],"an":[116],"optimal":[117],"$\\mathcal{O}(1/k)$":[118],"rate.":[119],"We":[120],"exemplify":[121],"on":[124],"compression":[129],"Our":[131],"experiments":[132],"validate":[133],"fast":[134],"convergence":[135],"with":[139],"step":[141],"decay":[142],"schedules.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}