{"id":"https://openalex.org/W803791801","doi":null,"title":"Accelerating Stochastic Gradient Descent via Online Learning to Sample","display_name":"Accelerating Stochastic Gradient Descent via Online Learning to Sample","publication_year":2015,"publication_date":"2015-06-30","ids":{"openalex":"https://openalex.org/W803791801","mag":"803791801"},"language":"en","primary_location":{"id":"mag:803791801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1506.09016","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1506.09016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090750283","display_name":"Guillaume Bouchard","orcid":"https://orcid.org/0009-0006-5332-0923","observed_orcids":["https://orcid.org/0009-0006-5332-0923","https://orcid.org/0009-0009-1506-0616"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Bouchard","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-5332-0923","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032987388","display_name":"Th\u00e9o Trouillon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Th\u00e9o Trouillon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113478975","display_name":"Julien P\u00e9rez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien P\u00e9rez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075018873","display_name":"Adrien Gaidon","orcid":"https://orcid.org/0000-0001-8820-550X","observed_orcids":["https://orcid.org/0000-0001-8820-550X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrien Gaidon","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":7,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/importance-sampling","display_name":"importance sampling","score":0.5860000252723694},{"id":"https://openalex.org/keywords/online-optimization","display_name":"online optimization","score":0.4950000047683716},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.7350000143051147},{"id":"https://openalex.org/keywords/matrix-factorization","display_name":"matrix factorization","score":0.9789999723434448},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8190000057220459}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8476744294166565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743701696395874},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5851937532424927},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5841001868247986},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5722646117210388},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5688347816467285},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5393549799919128},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49631720781326294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49033522605895996},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.47526901960372925},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.43717247247695923},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.4337950050830841},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.417946457862854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36596041917800903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614715337753296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28493380546569824},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1927289068698883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10447180271148682},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.08706504106521606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07421496510505676},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:803791801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1506.09016","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:803791801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1506.09016","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1516903196","https://openalex.org/W1568229137","https://openalex.org/W1994616650","https://openalex.org/W2023640363","https://openalex.org/W2086161653","https://openalex.org/W2096192494","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2113651538","https://openalex.org/W2119196781","https://openalex.org/W2143803054","https://openalex.org/W2146502635","https://openalex.org/W2152306708","https://openalex.org/W2152808281","https://openalex.org/W2155541015","https://openalex.org/W2156779765","https://openalex.org/W2161381512","https://openalex.org/W2161969291","https://openalex.org/W2166851633","https://openalex.org/W2171671424"],"related_works":["https://openalex.org/W2298052207","https://openalex.org/W2429473340","https://openalex.org/W2294540259","https://openalex.org/W2508844316","https://openalex.org/W2970617576","https://openalex.org/W2892283076","https://openalex.org/W2982657204","https://openalex.org/W4415111967","https://openalex.org/W2893302333","https://openalex.org/W3159953444"],"abstract_inverted_index":{"Stochastic":[0],"Gradient":[1],"Descent":[2],"(SGD)":[3],"is":[4],"one":[5],"of":[6,54,66,79,95,104,130],"the":[7,30,49,63,77,80,128,152,160],"most":[8,31],"widely":[9],"used":[10,46],"techniques":[11],"for":[12],"online":[13,73],"optimization":[14],"in":[15,117],"machine":[16],"learning.":[17],"In":[18],"this":[19],"work,":[20],"we":[21,40,60],"accelerate":[22],"SGD":[23,43,68,89],"by":[24,74],"adaptively":[25],"learning":[26,108],"how":[27],"to":[28,47,97,106],"sample":[29,107],"useful":[32],"training":[33],"examples":[34],"at":[35,159],"each":[36],"time":[37],"step.":[38],"First,":[39],"show":[41,61,111],"that":[42,62,112],"can":[44,70],"be":[45,71],"learn":[48],"best":[50],"possible":[51],"sampling":[52,57,64,129],"distribution":[53,65],"an":[55],"importance":[56],"estimator.":[58],"Second,":[59],"a":[67,93,102],"algorithm":[69,84],"estimated":[72,158],"incrementally":[75],"minimizing":[76],"variance":[78],"gradient.":[81],"The":[82],"resulting":[83],"-":[85,91],"called":[86],"Adaptive":[87],"Weighted":[88],"(AW-SGD)":[90],"maintains":[92],"set":[94,103],"parameters":[96,105],"optimize,":[98],"as":[99,101],"well":[100],"examples.":[109],"We":[110],"AW-SGD":[113],"yields":[114],"faster":[115],"convergence":[116],"three":[118],"different":[119],"applications:":[120],"(i)":[121],"image":[122],"classification":[123],"with":[124],"deep":[125],"features,":[126],"where":[127,139,151],"images":[131],"depends":[132],"on":[133],"their":[134],"labels,":[135],"(ii)":[136],"matrix":[137],"factorization,":[138],"rows":[140],"and":[141,147,154],"columns":[142],"are":[143,157],"not":[144],"sampled":[145],"uniformly,":[146],"(iii)":[148],"reinforcement":[149],"learning,":[150],"optimized":[153],"explore":[155],"policies":[156],"same":[161],"time.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}