{"id":"https://openalex.org/W7204868368","doi":"https://doi.org/10.48550/arxiv.2608.30254","title":"Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression","display_name":"Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204868368","doi":"https://doi.org/10.48550/arxiv.2608.30254"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30254","pdf_url":"https://arxiv.org/pdf/2608.30254","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/2608.30254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148775251","display_name":"Guangjian Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Guangjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5148775251"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.7143999934196472,"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":0.7143999934196472,"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":0.13179999589920044,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.036400001496076584,"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":0.8809999823570251},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"empirical risk minimization","score":0.7059999704360962},{"id":"https://openalex.org/keywords/frobenius-norm","display_name":"Frobenius norm","score":0.7839999794960022},{"id":"https://openalex.org/keywords/squared-error-loss","display_name":"squared error loss","score":0.7670000195503235},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6862999796867371},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C32224588","wikidata":"https://www.wikidata.org/wiki/Q7250175","display_name":"Proper linear model","level":4,"score":0.3666999936103821},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C135692309","wikidata":"https://www.wikidata.org/wiki/Q111124","display_name":"Square (algebra)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C136368487","wikidata":"https://www.wikidata.org/wiki/Q7979899","display_name":"Weighted median","level":5,"score":0.32089999318122864},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C2988709989","wikidata":"https://www.wikidata.org/wiki/Q85784623","display_name":"Mean square","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C70519679","wikidata":"https://www.wikidata.org/wiki/Q6666755","display_name":"Log-linear model","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30254","pdf_url":"https://arxiv.org/pdf/2608.30254","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.2608.30254","doi":"https://doi.org/10.48550/arxiv.2608.30254","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30254","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:2608.30254","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30254","pdf_url":"https://arxiv.org/pdf/2608.30254","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204868368.pdf","grobid_xml":"https://content.openalex.org/works/W7204868368.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4413740922","https://openalex.org/W6910417446","https://openalex.org/W7202181253","https://openalex.org/W7202191042","https://openalex.org/W7204761484"],"related_works":["https://openalex.org/W7202181253","https://openalex.org/W7204761484","https://openalex.org/W7216584435","https://openalex.org/W7218700930","https://openalex.org/W7203539485","https://openalex.org/W3204840012","https://openalex.org/W7098033967","https://openalex.org/W7097380888","https://openalex.org/W2118999374","https://openalex.org/W7097420404"],"abstract_inverted_index":{"We":[0,25,47,68,80],"resolve":[1],"the":[2,9,42,50,58,70,76,82],"threshold":[3],"part":[4],"of":[5,8,19,53],"Question":[6],"4":[7],"COLT":[10],"2025":[11],"open":[12],"problem":[13],"\"Data":[14],"Selection":[15],"for":[16,56,87,92],"Regression":[17],"Tasks\"":[18],"Hanneke,":[20],"Moran,":[21],"Shlimovich":[22],"and":[23,37,90],"Yehudayoff.":[24],"study":[26],"vector-valued":[27],"linear":[28],"regression":[29],"with":[30],"square":[31],"loss":[32,60],"$\\ell_{(x,y)}(W)=\\lVert":[33],"Wx-y\\rVert_2^2$,":[34],"where":[35],"$x\\in\\mathbb{R}^d$":[36],"$y\\in\\mathbb{R}^m$.":[38],"The":[39],"learner":[40],"returns":[41],"minimum-Frobenius-norm":[43],"empirical":[44],"risk":[45],"minimizer.":[46],"prove":[48],"that":[49],"minimal":[51],"budget":[52],"weighted":[54,71],"examples":[55],"recovering":[57],"full-data":[59],"on":[61],"every":[62,88],"finite":[63],"dataset":[64],"is":[65],"exactly":[66],"$n^{\\star}(d,m)=(m+1)d$.":[67],"determine":[69],"selection":[72],"profile":[73],"$F_{\\mathrm{weighted}}(d,m,n)$":[74],"at":[75],"near-threshold":[77],"budget:":[78],"$F_{\\mathrm{weighted}}(d,m,(m+1)d-1)=1+1/(dm^2)$.":[79],"recover":[81],"known":[83],"spanning-budget":[84],"value":[85],"$F_{\\mathrm{weighted}}(d,m,d)=d+1$":[86],"$m$,":[89],"$F_{\\mathrm{weighted}}(d,m,n)=\\infty$":[91],"$n":[93]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-02T00:00:00"}