{"id":"https://openalex.org/W2799151547","doi":"https://doi.org/10.1109/icpr.2018.8546186","title":"Effects of sampling skewness of the importance-weighted risk estimator on model selection","display_name":"Effects of sampling skewness of the importance-weighted risk estimator on model selection","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2799151547","doi":"https://doi.org/10.1109/icpr.2018.8546186","mag":"2799151547"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8546186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8546186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.07344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wouter Kouw","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Wouter Kouw","raw_affiliation_strings":["Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Loog","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Loog","raw_affiliation_strings":["Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.7322,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72563468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1468","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9987999796867371,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9987999796867371,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9824000000953674,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9797999858856201,"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/estimator","display_name":"Estimator","score":0.671999990940094},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.524399995803833},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.5116999745368958},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.48500001430511475},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.47839999198913574},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/bias-of-an-estimator","display_name":"Bias of an estimator","score":0.43149998784065247},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.3991999924182892}],"concepts":[{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.7541999816894531},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.671999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6175000071525574},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5126000046730042},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.47839999198913574},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C191393472","wikidata":"https://www.wikidata.org/wiki/Q15222032","display_name":"Bias of an estimator","level":4,"score":0.43149998784065247},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C164172150","wikidata":"https://www.wikidata.org/wiki/Q1782585","display_name":"Consistent estimator","level":4,"score":0.37940001487731934},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C133939421","wikidata":"https://www.wikidata.org/wiki/Q6865379","display_name":"Minimax estimator","level":4,"score":0.29339998960494995},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C102592046","wikidata":"https://www.wikidata.org/wiki/Q7504144","display_name":"Shrinkage estimator","level":5,"score":0.27799999713897705},{"id":"https://openalex.org/C2993010571","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Probability sampling","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C17648541","wikidata":"https://www.wikidata.org/wiki/Q2265984","display_name":"Efficiency","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C35594927","wikidata":"https://www.wikidata.org/wiki/Q2265984","display_name":"Efficient estimator","level":4,"score":0.2655999958515167},{"id":"https://openalex.org/C2779915747","wikidata":"https://www.wikidata.org/wiki/Q17058619","display_name":"Inverse probability weighting","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C82152865","wikidata":"https://www.wikidata.org/wiki/Q7208505","display_name":"Poisson sampling","level":5,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr.2018.8546186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8546186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.07344","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.07344","pdf_url":"https://arxiv.org/pdf/1804.07344","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.07344","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.07344","pdf_url":"https://arxiv.org/pdf/1804.07344","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1513873506","https://openalex.org/W1853837125","https://openalex.org/W1995945562","https://openalex.org/W2028138594","https://openalex.org/W2034368206","https://openalex.org/W2035956549","https://openalex.org/W2063471322","https://openalex.org/W2075851722","https://openalex.org/W2104094955","https://openalex.org/W2486672731","https://openalex.org/W6607672814","https://openalex.org/W6632916290","https://openalex.org/W6637386731","https://openalex.org/W6675547039","https://openalex.org/W6676997247","https://openalex.org/W6682197734","https://openalex.org/W6682981795","https://openalex.org/W6684642658","https://openalex.org/W7044050609"],"related_works":[],"abstract_inverted_index":{"Importance-weighting":[0],"is":[1],"a":[2,32],"popular":[3],"and":[4,13,24,62,88,103],"well-researched":[5],"technique":[6],"for":[7,63,73,91,115],"dealing":[8],"with":[9],"sample":[10,58,65],"selection":[11,59],"bias":[12,60],"covariate":[14],"shift.":[15],"It":[16],"has":[17],"desirable":[18],"characteristics":[19],"such":[20],"as":[21,38],"unbiasedness,":[22],"consistency":[23],"low":[25],"computational":[26],"complexity.":[27],"However,":[28],"weighting":[29],"can":[30,54],"have":[31],"detrimental":[33],"effect":[34],"on":[35],"an":[36,51],"estimator":[37,53,70],"well.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"empirically":[44],"show":[45],"that":[46],"the":[47,67,77,80,84,95,98,106],"sampling":[48,81,99],"distribution":[49],"of":[50,79,86,97,105],"importance-weighted":[52,68,116],"be":[55],"skewed.":[56],"For":[57],"settings,":[61],"small":[64],"sizes,":[66],"risk":[69,107],"produces":[71],"overestimates":[72],"data":[74,92],"sets":[75,93],"in":[76,94],"body":[78],"distribution,":[82],"i.e.":[83],"majority":[85],"cases,":[87],"large":[89],"underestimates":[90,104],"tail":[96],"distribution.":[100],"These":[101],"over-":[102],"lead":[108],"to":[109],"sub-optimal":[110],"regularization":[111],"parameters":[112],"when":[113],"used":[114],"validation.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-05-07T00:00:00"}