{"id":"https://openalex.org/W3034736247","doi":"https://doi.org/10.24963/ijcai.2020/374","title":"SVRG for Policy Evaluation with Fewer Gradient Evaluations","display_name":"SVRG for Policy Evaluation with Fewer Gradient Evaluations","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034736247","doi":"https://doi.org/10.24963/ijcai.2020/374","mag":"3034736247"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/374","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/374","pdf_url":"https://www.ijcai.org/proceedings/2020/0374.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0374.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024882659","display_name":"Zilun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Zilun Peng","raw_affiliation_strings":["Mila, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, McGill University","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ahmed Touati","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Ahmed Touati","raw_affiliation_strings":["Mila, Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103958886","display_name":"Pascal Vincent","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ","IL"],"is_corresponding":false,"raw_author_name":"Pascal Vincent","raw_affiliation_strings":["Facebook AI Research","Mila, Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Mila, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["Mila, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, McGill University","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.23,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4729736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2697","last_page":"2703"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9988999962806702,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6846359968185425},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6526492834091187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6448622345924377},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5903964042663574},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5590223073959351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5373614430427551},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5156804323196411},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46746280789375305},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.45829662680625916},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45662248134613037},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.45015639066696167},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43777328729629517},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4327925145626068},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4196881353855133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3010469079017639},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26085957884788513}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6846359968185425},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6526492834091187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448622345924377},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5903964042663574},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5590223073959351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5373614430427551},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5156804323196411},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46746280789375305},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.45829662680625916},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45662248134613037},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.45015639066696167},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43777328729629517},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4327925145626068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4196881353855133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3010469079017639},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26085957884788513},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/374","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/374","pdf_url":"https://www.ijcai.org/proceedings/2020/0374.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/374","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/374","pdf_url":"https://www.ijcai.org/proceedings/2020/0374.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034736247.pdf","grobid_xml":"https://content.openalex.org/works/W3034736247.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1646707810","https://openalex.org/W2075268401","https://openalex.org/W2107438106","https://openalex.org/W2121703796","https://openalex.org/W2121825831","https://openalex.org/W2132968152","https://openalex.org/W2165905123","https://openalex.org/W2395162158","https://openalex.org/W2519604671","https://openalex.org/W2586680856","https://openalex.org/W2617290556","https://openalex.org/W2752458704","https://openalex.org/W2950556355","https://openalex.org/W2952215077","https://openalex.org/W2963357609","https://openalex.org/W2963472288","https://openalex.org/W2964410826","https://openalex.org/W2996964934","https://openalex.org/W2999249710","https://openalex.org/W3034736247","https://openalex.org/W3041202696","https://openalex.org/W4241680091","https://openalex.org/W4289760659","https://openalex.org/W4298064558"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W3184322736","https://openalex.org/W3188986767"],"abstract_inverted_index":{"Stochastic":[0],"variance-reduced":[1],"gradient":[2,51,64,95],"(SVRG)":[3],"is":[4,126],"an":[5],"optimization":[6],"method":[7],"originally":[8],"designed":[9],"for":[10,26,86],"tackling":[11],"machine":[12],"learning":[13,33],"problems":[14],"with":[15,131],"a":[16,29,44,62,99],"finite":[17],"sum":[18],"structure.":[19],"SVRG":[20,47,60,85,123],"was":[21],"later":[22],"shown":[23],"to":[24,38,72,114,128],"work":[25],"policy":[27,87,129],"evaluation,":[28],"problem":[30],"in":[31,34,119],"reinforcement":[32],"which":[35,69],"one":[36,110],"aims":[37],"estimate":[39],"the":[40,57,66,92,116,143],"value":[41],"function":[42,133],"of":[43,50,84,94,122],"given":[45],"policy.":[46],"makes":[48],"use":[49,115],"estimates":[52],"at":[53],"two":[54,82],"scales.":[55],"At":[56],"slower":[58],"scale,":[59],"computes":[61],"full":[63],"over":[65],"whole":[67],"dataset,":[68],"could":[70,89],"lead":[71],"prohibitive":[73],"computation":[74],"costs.":[75],"In":[76],"this":[77],"work,":[78],"we":[79],"show":[80],"that":[81,109],"variants":[83],"evaluation":[88,130],"significantly":[90],"diminish":[91],"number":[93],"calculations":[96],"while":[97],"preserving":[98],"linear":[100,132],"convergence":[101],"speed.":[102],"More":[103],"importantly,":[104],"our":[105],"theoretical":[106],"result":[107],"implies":[108],"does":[111],"not":[112],"need":[113],"entire":[117],"dataset":[118],"every":[120],"epoch":[121],"when":[124],"it":[125],"applied":[127],"approximation.":[134],"Our":[135],"experiments":[136],"demonstrate":[137],"large":[138],"computational":[139],"savings":[140],"provided":[141],"by":[142],"proposed":[144],"methods.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}