{"id":"https://openalex.org/W2964039533","doi":"https://doi.org/10.1109/tkde.2016.2604302","title":"Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization","display_name":"Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization","publication_year":2016,"publication_date":"2016-08-30","ids":{"openalex":"https://openalex.org/W2964039533","doi":"https://doi.org/10.1109/tkde.2016.2604302","mag":"2964039533"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2604302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2604302","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","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/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076498350","display_name":"Xiaobai Liu","orcid":"https://orcid.org/0000-0002-2086-5410"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobai Liu","raw_affiliation_strings":["San Diego State University, CA"],"affiliations":[{"raw_affiliation_string":"San Diego State University, CA","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100737174","display_name":"Wei Fan","orcid":"https://orcid.org/0000-0002-1247-2131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Fan","raw_affiliation_strings":["Baidu Big Data Research Lab, Sunny Vale, CA"],"affiliations":[{"raw_affiliation_string":"Baidu Big Data Research Lab, Sunny Vale, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028877572"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":3.4278,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93969042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":"2","first_page":"458","last_page":"471"},"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":0.9997000098228455,"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/T10057","display_name":"Face and Expression Recognition","score":0.998199999332428,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.882073700428009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6040728092193604},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5814223885536194},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5327883362770081},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4902339577674866},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4798016846179962},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4743277430534363},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.45665442943573},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4541170597076416},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4328700006008148},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.42911091446876526},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.42465081810951233},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39728787541389465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3210422396659851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15159812569618225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14737382531166077},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.12257170677185059},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12164363265037537}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.882073700428009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040728092193604},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5814223885536194},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5327883362770081},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4902339577674866},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4798016846179962},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4743277430534363},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45665442943573},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4541170597076416},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4328700006008148},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.42911091446876526},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.42465081810951233},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39728787541389465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3210422396659851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15159812569618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14737382531166077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.12257170677185059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12164363265037537},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2016.2604302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2604302","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1500351990","https://openalex.org/W1516903196","https://openalex.org/W1520129216","https://openalex.org/W1523661875","https://openalex.org/W1524688041","https://openalex.org/W1791038712","https://openalex.org/W1842094663","https://openalex.org/W1980147176","https://openalex.org/W2006815170","https://openalex.org/W2047152541","https://openalex.org/W2072566913","https://openalex.org/W2103972604","https://openalex.org/W2106728335","https://openalex.org/W2107438106","https://openalex.org/W2108948681","https://openalex.org/W2113097878","https://openalex.org/W2121966774","https://openalex.org/W2130062883","https://openalex.org/W2134563198","https://openalex.org/W2135670105","https://openalex.org/W2138972044","https://openalex.org/W2140214528","https://openalex.org/W2145832734","https://openalex.org/W2147898188","https://openalex.org/W2156909104","https://openalex.org/W2189508540","https://openalex.org/W2951488730","https://openalex.org/W2963992805","https://openalex.org/W4205947740","https://openalex.org/W6629858893","https://openalex.org/W6630841318","https://openalex.org/W6631443459","https://openalex.org/W6638407692","https://openalex.org/W6638704708","https://openalex.org/W6640396632","https://openalex.org/W6675995183","https://openalex.org/W6676105031","https://openalex.org/W6677064947","https://openalex.org/W6679314259","https://openalex.org/W6679809621","https://openalex.org/W6680213789","https://openalex.org/W6680443865","https://openalex.org/W6680610635","https://openalex.org/W6681468881","https://openalex.org/W6687078384","https://openalex.org/W6818868544"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3109737792","https://openalex.org/W3109198354","https://openalex.org/W2760303966","https://openalex.org/W2964140730","https://openalex.org/W937081240"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1,21,67,81,92,145,175],"descent":[2,68,93],"(SGD)":[3],"holds":[4],"as":[5,32],"a":[6,26,37,88,105,169],"classical":[7],"method":[8],"to":[9,45,96,121,167],"build":[10],"large":[11,106],"scale":[12],"machine":[13],"learning":[14],"models":[15],"over":[16],"big":[17],"data.":[18],"A":[19],"stochastic":[20,56],"is":[22,146,165,210],"typically":[23],"calculated":[24,147],"from":[25,73,123,176],"limited":[27],"number":[28],"of":[29,55,64,104,108,172,208],"samples":[30],"(known":[31],"mini-batch),":[33],"which":[34,70,127,153],"potentially":[35],"incurs":[36],"high":[38,124],"variance":[39],"and":[40,200],"causes":[41],"the":[42,48,53,62,102,143,173,187,192,198,204],"estimated":[43],"parameters":[44],"bounce":[46],"around":[47],"optimal":[49],"solution.":[50],"To":[51],"improve":[52],"stability":[54],"gradient,":[57],"recent":[58],"years":[59],"have":[60],"witnessed":[61],"proposal":[63],"several":[65,215],"semi-stochastic":[66,91,117,144],"algorithms,":[69],"distinguish":[71],"themselves":[72],"standard":[74],"SGD":[75,133],"by":[76,158],"incorporating":[77],"global":[78],"information":[79],"into":[80],"computation.":[82],"In":[83,139],"this":[84,97],"paper,":[85],"we":[86],"contribute":[87],"novel":[89],"stratified":[90],"(S3GD)":[94],"algorithm":[95],"nascent":[98],"research":[99],"area,":[100],"accelerating":[101],"optimization":[103],"family":[107],"composite":[109],"convex":[110],"functions.":[111],"Though":[112],"theoretically":[113],"converging":[114],"faster,":[115],"prior":[116],"algorithms":[118],"are":[119],"found":[120],"suffer":[122],"iteration":[125],"complexity,":[126],"makes":[128],"them":[129],"even":[130],"slower":[131],"than":[132],"in":[134],"practice":[135],"on":[136,149,214],"many":[137],"datasets.":[138,218],"our":[140],"proposed":[141,188],"S3GD,":[142],"based":[148],"efficient":[150],"manifold":[151],"propagation,":[152],"can":[154],"be":[155],"numerically":[156],"accomplished":[157],"sparse":[159],"matrix":[160],"multiplications.":[161],"This":[162],"way":[163],"S3GD":[164,189,209],"able":[166],"generate":[168],"highly-accurate":[170],"estimate":[171],"exact":[174],"each":[177],"mini-batch":[178],"with":[179],"largely-reduced":[180],"computational":[181],"complexity.":[182],"Theoretic":[183],"analysis":[184],"reveals":[185],"that":[186],"elegantly":[190],"balances":[191],"geometric":[193],"algorithmic":[194],"convergence":[195],"rate":[196],"against":[197],"space":[199],"time":[201],"complexities":[202],"during":[203],"optimization.":[205],"The":[206],"efficacy":[207],"also":[211],"experimentally":[212],"corroborated":[213],"large-scale":[216],"benchmark":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}