{"id":"https://openalex.org/W2947798871","doi":"https://doi.org/10.24963/ijcai.2019/544","title":"Reparameterizable Subset Sampling via Continuous Relaxations","display_name":"Reparameterizable Subset Sampling via Continuous Relaxations","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2947798871","doi":"https://doi.org/10.24963/ijcai.2019/544","mag":"2947798871"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/544","pdf_url":"https://www.ijcai.org/proceedings/2019/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0544.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069097726","display_name":"Sang Michael Xie","orcid":"https://orcid.org/0000-0002-0820-2753"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sang Michael Xie","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113804858","display_name":"Stefano Ermon","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefano Ermon","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3919","last_page":"3925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/sampling","display_name":"Sampling (signal processing)","score":0.7365856766700745},{"id":"https://openalex.org/keywords/gumbel-distribution","display_name":"Gumbel distribution","score":0.6789259910583496},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.629881739616394},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5996133685112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5686450600624084},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5609780550003052},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5560998916625977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5147402286529541},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5115314722061157},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5040299296379089},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4686189293861389},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46228909492492676},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4140397310256958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3794266879558563},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36603742837905884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.361021488904953},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22386816143989563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1412161886692047},{"id":"https://openalex.org/keywords/extreme-value-theory","display_name":"Extreme value theory","score":0.12360715866088867}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7365856766700745},{"id":"https://openalex.org/C137610916","wikidata":"https://www.wikidata.org/wiki/Q1096862","display_name":"Gumbel distribution","level":3,"score":0.6789259910583496},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.629881739616394},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5996133685112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5686450600624084},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5609780550003052},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5560998916625977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5147402286529541},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5115314722061157},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5040299296379089},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4686189293861389},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46228909492492676},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4140397310256958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3794266879558563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36603742837905884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.361021488904953},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22386816143989563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1412161886692047},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.12360715866088867},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2019/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/544","pdf_url":"https://www.ijcai.org/proceedings/2019/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.10517","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10517","pdf_url":"https://arxiv.org/pdf/1901.10517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2947798871","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1901.10517.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.1901.10517","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.10517","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/544","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/544","pdf_url":"https://www.ijcai.org/proceedings/2019/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2781775652","display_name":"CAREER: Modeling and Inference for Large Scale Spatio-Temporal Data","funder_award_id":"1651565","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3100523009","display_name":null,"funder_award_id":"FA9550-19-1-0024","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7963269316","display_name":"AitF: Collaborative Research: Efficient High-Dimensional Integration using Error-Correcting Codes","funder_award_id":"1733686","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947798871.pdf","grobid_xml":"https://content.openalex.org/works/W2947798871.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W28414123","https://openalex.org/W1514535095","https://openalex.org/W1832693441","https://openalex.org/W1982682305","https://openalex.org/W2113459411","https://openalex.org/W2116516955","https://openalex.org/W2119717200","https://openalex.org/W2119885577","https://openalex.org/W2134445663","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2563071247","https://openalex.org/W2565378226","https://openalex.org/W2949416428","https://openalex.org/W2950752421","https://openalex.org/W2951004968","https://openalex.org/W2963247666","https://openalex.org/W2963365341","https://openalex.org/W2963549470","https://openalex.org/W2963614749"],"related_works":["https://openalex.org/W2964554227","https://openalex.org/W2561856247","https://openalex.org/W3007433559","https://openalex.org/W2132217936","https://openalex.org/W2979454412","https://openalex.org/W2909150929","https://openalex.org/W2613223211","https://openalex.org/W3193954868","https://openalex.org/W2724116567","https://openalex.org/W1600761772","https://openalex.org/W2172298484","https://openalex.org/W2161777432","https://openalex.org/W3196423891","https://openalex.org/W3101685104","https://openalex.org/W199156503","https://openalex.org/W2696200655","https://openalex.org/W3007486107","https://openalex.org/W156854920","https://openalex.org/W2952141364","https://openalex.org/W1508542069"],"abstract_inverted_index":{"Many":[0],"machine":[1],"learning":[2],"tasks":[3,126],"require":[4],"sampling":[5,49,65,130],"a":[6,11,15,26,60,98],"subset":[7,48,64,129],"of":[8,40,63,82,94,106,117],"items":[9],"from":[10],"collection":[12],"based":[13],"on":[14],"parameterized":[16],"distribution.":[17,43],"The":[18],"Gumbel-softmax":[19],"trick":[20],"can":[21],"be":[22],"used":[23],"to":[24,37,79,96,108],"sample":[25,80],"single":[27],"item,":[28],"and":[29,104],"allows":[30],"for":[31,90],"low-variance":[32],"reparameterized":[33],"gradients":[34,69],"with":[35],"respect":[36],"the":[38,41,72,115],"parameters":[39],"underlying":[42],"However,":[44],"stochastic":[45,100],"optimization":[46],"involving":[47],"is":[50],"typically":[51],"not":[52],"reparameterizable.":[53],"To":[54],"overcome":[55],"this":[56,77],"limitation,":[57],"we":[58],"define":[59],"continuous":[61],"relaxation":[62],"that":[66],"provides":[67],"reparameterization":[68],"by":[70,112,127],"generalizing":[71],"Gumbel-max":[73],"trick.":[74],"We":[75,120],"use":[76],"approach":[78],"subsets":[81,93],"features":[83],"in":[84,123,131],"an":[85],"instance-wise":[86],"feature":[87],"selection":[88],"task":[89],"model":[91],"interpretability,":[92],"neighbors":[95,102,107],"implement":[97,109],"deep":[99],"k-nearest":[101],"model,":[103],"sub-sequences":[105],"parametric":[110],"t-SNE":[111],"directly":[113],"comparing":[114],"identities":[116],"local":[118],"neighbors.":[119],"improve":[121],"performance":[122],"all":[124],"these":[125],"incorporating":[128],"end-to-end":[132],"training.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}