{"id":"https://openalex.org/W7204761484","doi":"https://doi.org/10.48550/arxiv.2608.28007","title":"Exact Risk Ratios for Weighted Data Selection in Linear Regression","display_name":"Exact Risk Ratios for Weighted Data Selection in Linear Regression","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204761484","doi":"https://doi.org/10.48550/arxiv.2608.28007"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28007","pdf_url":"https://arxiv.org/pdf/2608.28007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148775251","display_name":"Guangjian Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhang, Guangjian","raw_affiliation_strings":["University of New South Wales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5148775251"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.296099990606308,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.296099990606308,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2766000032424927,"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":0.2678000032901764,"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/dataset-selection","display_name":"data selection","score":0.7020000219345093},{"id":"https://openalex.org/keywords/weighted-data","display_name":"weighted data","score":0.5519999861717224},{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.8640000224113464},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"empirical risk minimization","score":0.7009999752044678},{"id":"https://openalex.org/keywords/minimum-norm-solution","display_name":"minimum norm solution","score":0.7609999775886536},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.4790000021457672},{"id":"https://openalex.org/keywords/worst-case-analysis","display_name":"worst-case analysis","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6474999785423279},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2962000072002411},{"id":"https://openalex.org/C169241690","wikidata":"https://www.wikidata.org/wiki/Q7828122","display_name":"Total least squares","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C188649462","wikidata":"https://www.wikidata.org/wiki/Q2246261","display_name":"Generalized least squares","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28007","pdf_url":"https://arxiv.org/pdf/2608.28007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.28007","doi":"https://doi.org/10.48550/arxiv.2608.28007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28007","pdf_url":"https://arxiv.org/pdf/2608.28007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204761484.pdf","grobid_xml":"https://content.openalex.org/works/W7204761484.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3010878999","https://openalex.org/W6910417446","https://openalex.org/W7202181253"],"related_works":["https://openalex.org/W7204868368","https://openalex.org/W7216584435","https://openalex.org/W7202181253","https://openalex.org/W7218700930","https://openalex.org/W7203539485","https://openalex.org/W6910417446","https://openalex.org/W3204840012","https://openalex.org/W4406139704","https://openalex.org/W2006016498","https://openalex.org/W7133201041"],"abstract_inverted_index":{"How":[0],"much":[1],"data":[2],"must":[3],"a":[4,30],"fixed":[5],"learner":[6],"retain?":[7],"Hanneke,":[8],"Moran,":[9],"Shlimovich":[10],"and":[11,44,58],"Yehudayoff":[12],"(COLT":[13],"2025)":[14],"posed":[15],"this":[16],"question":[17],"for":[18,66],"linear":[19],"regression":[20],"with":[21,41],"the":[22,47,51,55,59],"minimum-norm":[23],"empirical":[24],"risk":[25],"minimizer.":[26],"A":[27],"selector":[28],"sees":[29],"finite":[31],"dataset":[32],"$D\\subseteq":[33],"R^d\\times":[34],"R$,":[35],"keeps":[36],"at":[37],"most":[38],"$n$":[39],"examples":[40],"nonnegative":[42],"weights,":[43],"$F_w(d,n)$":[45],"is":[46,64],"worst-case":[48],"ratio":[49],"between":[50],"full-data":[52],"loss":[53],"of":[54],"trained":[56],"predictor":[57],"optimal":[60],"loss.":[61],"The":[62],"value":[63],"$\\infty$":[65],"$n":[67]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-01T00:00:00"}