{"id":"https://openalex.org/W2950942124","doi":"https://doi.org/10.1609/aaai.v30i1.10200","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","display_name":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","publication_year":2016,"publication_date":"2016-02-21","ids":{"openalex":"https://openalex.org/W2950942124","doi":"https://doi.org/10.1609/aaai.v30i1.10200","mag":"2950942124"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v30i1.10200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10200/10059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10200/10059","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101417967","display_name":"Chunyuan Li","orcid":"https://orcid.org/0000-0003-1271-9605"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunyuan Li","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114686221","display_name":"Changyou Chen","orcid":"https://orcid.org/0000-0002-9877-8448"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changyou Chen","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052576907","display_name":"David Carlson","orcid":"https://orcid.org/0000-0003-1005-6385"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Carlson","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Carin","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101417967"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":9.6492,"has_fulltext":true,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99074074,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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/langevin-dynamics","display_name":"Langevin dynamics","score":0.7206897139549255},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6427807211875916},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6392083764076233},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.4937795102596283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4742131233215332},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4700680375099182},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4598459005355835},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4301999509334564},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.4121495485305786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3636404871940613},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35300466418266296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28692924976348877},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.11292889714241028},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1093137264251709}],"concepts":[{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.7206897139549255},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6427807211875916},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6392083764076233},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.4937795102596283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4742131233215332},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4700680375099182},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4598459005355835},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4301999509334564},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.4121495485305786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3636404871940613},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35300466418266296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28692924976348877},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.11292889714241028},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1093137264251709},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v30i1.10200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10200/10059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/10200","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/10200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"Peer-reviewed Article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v30i1.10200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10200/10059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950942124.pdf","grobid_xml":"https://content.openalex.org/works/W2950942124.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W6908809","https://openalex.org/W123701566","https://openalex.org/W582134693","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1536816303","https://openalex.org/W1545319692","https://openalex.org/W1567512734","https://openalex.org/W1592410721","https://openalex.org/W1719489212","https://openalex.org/W1737237432","https://openalex.org/W1772464306","https://openalex.org/W1826234144","https://openalex.org/W1907282891","https://openalex.org/W2049882758","https://openalex.org/W2095705004","https://openalex.org/W2102017903","https://openalex.org/W2110529144","https://openalex.org/W2111051539","https://openalex.org/W2115031564","https://openalex.org/W2115067168","https://openalex.org/W2130942839","https://openalex.org/W2144193737","https://openalex.org/W2146502635","https://openalex.org/W2146989110","https://openalex.org/W2150807068","https://openalex.org/W2161340280","https://openalex.org/W2163605009","https://openalex.org/W2165652770","https://openalex.org/W2167433878","https://openalex.org/W2185758820","https://openalex.org/W2186210550","https://openalex.org/W2234809627","https://openalex.org/W2546302380","https://openalex.org/W2949442184","https://openalex.org/W2949888546","https://openalex.org/W2950177356","https://openalex.org/W2950200612","https://openalex.org/W2950980440","https://openalex.org/W2951037516","https://openalex.org/W2951105989","https://openalex.org/W2951266961","https://openalex.org/W2951595529","https://openalex.org/W2963574257","https://openalex.org/W2963586744","https://openalex.org/W2963606038","https://openalex.org/W2964121744","https://openalex.org/W3037950864","https://openalex.org/W3118608800","https://openalex.org/W4301437408","https://openalex.org/W6600213771","https://openalex.org/W6631190155","https://openalex.org/W6632084258","https://openalex.org/W6633735129","https://openalex.org/W6635477909","https://openalex.org/W6638444622","https://openalex.org/W6638674303","https://openalex.org/W6679436768","https://openalex.org/W6681286327","https://openalex.org/W6696761078","https://openalex.org/W6764214684","https://openalex.org/W6818868544"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204","https://openalex.org/W757031997"],"abstract_inverted_index":{"Effective":[0],"training":[1],"of":[2,18,48,107],"deep":[3],"neural":[4],"networks":[5],"suffers":[6],"from":[7],"two":[8],"main":[9],"issues.":[10],"The":[11,75],"first":[12],"is":[13,54,57],"that":[14,68,136],"the":[15,45,88],"parameter":[16,49],"space":[17],"these":[19,145],"models":[20],"exhibit":[21],"pathological":[22],"curvature.":[23],"Recent":[24],"methods":[25,39,95],"address":[26],"this":[27,73,108],"problem":[28],"by":[29,42,60,80],"using":[30,81],"adaptive":[31,101],"preconditioning":[32],"for":[33,125],"Stochastic":[34,82],"Gradient":[35,83],"Descent":[36],"(SGD).":[37],"These":[38],"improve":[40],"convergence":[41,116],"adapting":[43],"to":[44],"local":[46],"geometry":[47],"space.":[50],"A":[51],"second":[52],"issue":[53],"overfitting,":[55],"which":[56],"typically":[58],"addressed":[59],"early":[61],"stopping.":[62],"However,":[63,87],"recent":[64],"work":[65],"has":[66],"demonstrated":[67],"Bayesian":[69],"model":[70],"averaging":[71],"mitigates":[72],"problem.":[74],"posterior":[76],"can":[77],"be":[78],"sampled":[79],"Langevin":[84],"Dynamics":[85],"(SGLD).":[86],"rapidly":[89],"changing":[90],"curvature":[91],"renders":[92],"default":[93],"SGLD":[94,139],"inefficient.":[96],"Here,":[97],"we":[98,110],"propose":[99],"combining":[100],"preconditioners":[102],"with":[103],"SGLD.":[104],"In":[105],"support":[106],"idea,":[109],"give":[111],"theoretical":[112],"properties":[113],"on":[114,144],"asymptotic":[115],"and":[117,131],"predictive":[118],"risk.":[119],"We":[120],"also":[121],"provide":[122],"empirical":[123],"results":[124],"Logistic":[126],"Regression,":[127],"Feedforward":[128],"Neural":[129,133],"Nets,":[130,134],"Convolutional":[132],"demonstrating":[135],"our":[137],"preconditioned":[138],"method":[140],"gives":[141],"state-of-the-art":[142],"performance":[143],"models.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}