{"id":"https://openalex.org/W2962985678","doi":"https://doi.org/10.1609/aaai.v33i01.33014181","title":"Lifted Proximal Operator Machines","display_name":"Lifted Proximal Operator Machines","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2962985678","doi":"https://doi.org/10.1609/aaai.v33i01.33014181","mag":"2962985678"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4323/4201","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/4323/4201","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084715845","display_name":"Jia Li","orcid":"https://orcid.org/0000-0003-0307-3814"},"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":"Jia Li","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008843158","display_name":"Cong Fang","orcid":"https://orcid.org/0000-0002-5076-7897"},"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":false,"raw_author_name":"Cong Fang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016399094","display_name":"Zhouchen Lin","orcid":"https://orcid.org/0000-0003-1493-7569"},"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":false,"raw_author_name":"Zhouchen Lin","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084715845"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.6603,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91676515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"4181","last_page":"4188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T12676","display_name":"Machine Learning and ELM","score":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9940000176429749,"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":0.7031493186950684},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6847418546676636},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.6155521869659424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6149929761886597},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5887189507484436},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5706886053085327},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.567514181137085},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5584843158721924},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5462994575500488},{"id":"https://openalex.org/keywords/proximal-gradient-methods","display_name":"Proximal Gradient Methods","score":0.5218483209609985},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.5199097990989685},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5074848532676697},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.475012868642807},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4678436517715454},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4414242208003998},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.43880704045295715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33355581760406494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27261531352996826},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10835579037666321}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7031493186950684},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6847418546676636},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6155521869659424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149929761886597},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5887189507484436},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5706886053085327},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.567514181137085},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5584843158721924},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5462994575500488},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.5218483209609985},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.5199097990989685},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5074848532676697},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.475012868642807},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4678436517715454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4414242208003998},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.43880704045295715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33355581760406494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27261531352996826},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10835579037666321},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4323/4201","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4323/4201","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G229839104","display_name":null,"funder_award_id":"61625301 and 61731018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3503326317","display_name":null,"funder_award_id":"2015CB352502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4590404751","display_name":null,"funder_award_id":"61625301","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5241535071","display_name":null,"funder_award_id":"61731018","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7483285578","display_name":null,"funder_award_id":"61625301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8208342437","display_name":null,"funder_award_id":"1 and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G940306304","display_name":null,"funder_award_id":"61731018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962985678.pdf","grobid_xml":"https://content.openalex.org/works/W2962985678.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1697075315","https://openalex.org/W1772464306","https://openalex.org/W1833744030","https://openalex.org/W2100549954","https://openalex.org/W2100556411","https://openalex.org/W2102017903","https://openalex.org/W2107221565","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2335728318","https://openalex.org/W2346438296","https://openalex.org/W2400146652","https://openalex.org/W2769449302","https://openalex.org/W2950094539","https://openalex.org/W2950452769","https://openalex.org/W2951085447","https://openalex.org/W2952230511","https://openalex.org/W2962817490","https://openalex.org/W3118608800","https://openalex.org/W4293877733","https://openalex.org/W4294635596","https://openalex.org/W4295262505","https://openalex.org/W6683738474","https://openalex.org/W6687483927","https://openalex.org/W6693397755","https://openalex.org/W6758920291"],"related_works":["https://openalex.org/W3116943156","https://openalex.org/W4322631263","https://openalex.org/W3012219884","https://openalex.org/W4366999905","https://openalex.org/W2936783136","https://openalex.org/W4315785049","https://openalex.org/W3015792155","https://openalex.org/W3173926637","https://openalex.org/W2937906318","https://openalex.org/W3118286710"],"abstract_inverted_index":{"We":[0,151],"propose":[1],"a":[2,23],"new":[3],"optimization":[4,168],"method":[5,103],"for":[6],"training":[7,99],"feedforward":[8,24],"neural":[9,25],"networks.":[10],"By":[11],"rewriting":[12],"the":[13,29,33,41,67,77,80,90,127,133,154,158,167,184],"activation":[14,81,111],"function":[15,35,82],"as":[16,36,138],"an":[17],"equivalent":[18],"proximal":[19,30,43],"operator,":[20],"we":[21,39,74],"approximate":[22],"network":[26],"by":[27,173],"adding":[28],"operators":[31],"to":[32,60,65,106,183],"objective":[34],"penalties,":[37],"hence":[38],"call":[40],"lifted":[42],"operator":[44],"machine":[45],"(LPOM).":[46],"LPOM":[47,119],"is":[48,104,147],"block":[49,62],"multiconvex":[50],"in":[51,96],"all":[52],"layer-wise":[53,68,128,159],"weights":[54,69,160],"and":[55,70,117,161,163,179],"activations.":[56,71],"This":[57],"allows":[58],"us":[59],"use":[61,76],"coordinate":[63],"descent":[64,141],"update":[66],"Most":[72],"notably,":[73],"only":[75],"mapping":[78],"of":[79,136,156,186],"itself,":[83],"rather":[84],"than":[85,126],"its":[86],"derivative,":[87],"thus":[88,130],"avoiding":[89],"gradient":[91,97,140],"vanishing":[92],"or":[93],"blow-up":[94],"issues":[95],"based":[98],"methods.":[100],"So":[101],"our":[102],"applicable":[105],"various":[107],"non-decreasing":[108],"Lipschitz":[109],"continuous":[110],"functions,":[112],"which":[113],"can":[114],"be":[115,170],"saturating":[116],"non-differentiable.":[118],"does":[120],"not":[121],"require":[122],"more":[123],"auxiliary":[124],"variables":[125],"activations,":[129],"using":[131],"roughly":[132],"same":[134],"amount":[135],"memory":[137],"stochastic":[139],"(SGD)":[142],"does.":[143],"Its":[144],"parameter":[145],"tuning":[146],"also":[148],"much":[149],"simpler.":[150],"further":[152],"prove":[153],"convergence":[155],"updating":[157],"activations":[162],"point":[164],"out":[165],"that":[166],"could":[169],"made":[171],"parallel":[172],"asynchronous":[174],"update.":[175],"Experiments":[176],"on":[177],"MNIST":[178],"CIFAR-10":[180],"datasets":[181],"testify":[182],"advantages":[185],"LPOM.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}