{"id":"https://openalex.org/W2963324739","doi":"https://doi.org/10.48550/arxiv.1705.06908","title":"Unbiased estimates for linear regression via volume sampling","display_name":"Unbiased estimates for linear regression via volume sampling","alternate_titles":[],"publication_year":2017,"publication_date":"2017-05-19","ids":{"openalex":"https://openalex.org/W2963324739","doi":"https://doi.org/10.48550/arxiv.1705.06908","mag":"2963324739"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1705.06908","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.06908","pdf_url":"https://arxiv.org/pdf/1705.06908","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"},"parent_works":[],"lineage":["https://openalex.org/W2963324739"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.06908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013422880","display_name":"Micha\u0142 Derezi\u0144ski","orcid":"https://orcid.org/0009-0001-7274-539X","observed_orcids":["https://orcid.org/0009-0001-7274-539X"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Derezi\u0144ski, Micha\u0142","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, United States","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108549518","display_name":"Manfred K. Warmuth","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Warmuth, Manfred K.","raw_affiliation_strings":["Department of Computer Science University of California Santa Cruz","University of California System, Oakland, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of California Santa Cruz","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California System, Oakland, United States","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"3084","last_page":"3093"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4993000030517578,"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":0.4993000030517578,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.12710000574588776,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.07500000298023224,"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/volume-sampling","display_name":"volume sampling","score":0.9940000176429749},{"id":"https://openalex.org/keywords/unbiased-estimators","display_name":"unbiased estimators","score":0.7559999823570251},{"id":"https://openalex.org/keywords/linear-least-squares","display_name":"linear least squares","score":0.9259999990463257},{"id":"https://openalex.org/keywords/column-sampling","display_name":"column sampling","score":0.5709999799728394},{"id":"https://openalex.org/keywords/full-rank-matrices","display_name":"full rank matrices","score":0.5630000233650208},{"id":"https://openalex.org/keywords/label-efficient-learning","display_name":"label-efficient learning","score":0.41600000858306885},{"id":"https://openalex.org/keywords/sampling-algorithms","display_name":"sampling algorithms","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7595977783203125},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6110642552375793},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5963950157165527},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5506502985954285},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.5130597352981567},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5065819025039673},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4843050539493561},{"id":"https://openalex.org/C169241690","wikidata":"https://www.wikidata.org/wiki/Q7828122","display_name":"Total least squares","level":3,"score":0.47632819414138794},{"id":"https://openalex.org/C58663186","wikidata":"https://www.wikidata.org/wiki/Q6553462","display_name":"Linear least squares","level":3,"score":0.4593300223350525},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.4590131342411041},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.435464471578598},{"id":"https://openalex.org/C103545067","wikidata":"https://www.wikidata.org/wiki/Q796265","display_name":"Best linear unbiased prediction","level":3,"score":0.43417850136756897},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4198472499847412},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.416795015335083},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41141754388809204},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38722407817840576},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.32693129777908325},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2223168909549713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.13362163305282593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1705.06908","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.06908","pdf_url":"https://arxiv.org/pdf/1705.06908","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.1705.06908","doi":"https://doi.org/10.48550/arxiv.1705.06908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.06908","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"},{"id":"mag:2963324739","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/6901-unbiased-estimates-for-linear-regression-via-volume-sampling.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":"https://openalex.org/P4404678063","host_organization_name":"Neural Information Processing Systems Foundation","host_organization_lineage":["https://openalex.org/P4404678063"],"host_organization_lineage_names":["Neural Information Processing Systems Foundation"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.06908","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.06908","pdf_url":"https://arxiv.org/pdf/1705.06908","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":[{"id":"https://openalex.org/G4299139032","display_name":"RI: Small: Collaborative Research: On-Line Learning Algorithms for Path Experts with Non-Additive Losses","funder_award_id":"1619271","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963324739.pdf","grobid_xml":"https://content.openalex.org/works/W2963324739.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1526259142","https://openalex.org/W1570963478","https://openalex.org/W1605768620","https://openalex.org/W1992065791","https://openalex.org/W1998269045","https://openalex.org/W1999352252","https://openalex.org/W2026386069","https://openalex.org/W2045390367","https://openalex.org/W2064583534","https://openalex.org/W2089135543","https://openalex.org/W2101043704","https://openalex.org/W2103318769","https://openalex.org/W2107411554","https://openalex.org/W2138779671","https://openalex.org/W2144578442","https://openalex.org/W2148516480","https://openalex.org/W2150907712","https://openalex.org/W2187580259","https://openalex.org/W2517069687","https://openalex.org/W2616345629","https://openalex.org/W2728264528","https://openalex.org/W2766036709","https://openalex.org/W2949212323","https://openalex.org/W2962759069","https://openalex.org/W4243341520","https://openalex.org/W4244670803"],"related_works":["https://openalex.org/W2806315060","https://openalex.org/W2807660787","https://openalex.org/W2897037976","https://openalex.org/W2954491832","https://openalex.org/W2963693254","https://openalex.org/W2766036709","https://openalex.org/W4312535585","https://openalex.org/W2043804332","https://openalex.org/W7220962367"],"abstract_inverted_index":{"Given":[0],"a":[1,26,82,87,110,179],"full":[2],"rank":[3],"matrix":[4],"$X$":[5],"with":[6],"more":[7],"columns":[8,30,49,134],"than":[9,203],"rows,":[10],"consider":[11],"the":[12,16,22,35,46,54,59,62,75,78,100,127,130,145,149,152,160,164,210,214],"task":[13],"of":[14,25,29,37,48,61,77,115,133,148,159,213],"estimating":[15],"pseudo":[17,23],"inverse":[18,24,93],"$X^+$":[19],"based":[20,167],"on":[21,168,218],"sampled":[27],"subset":[28,47,132],"(of":[31],"size":[32],"at":[33],"least":[34,102,184],"number":[36],"rows).":[38],"We":[39,117,172,189],"show":[40,143],"that":[41,144,174,200],"this":[42],"is":[43,50,71,155,201],"possible":[44],"if":[45],"chosen":[51,63],"proportional":[52],"to":[53,108,193],"squared":[55],"volume":[56,66,187,198],"spanned":[57],"by":[58],"rows":[60],"submatrix":[64],"(ie,":[65],"sampling).":[67],"The":[68],"resulting":[69],"estimator":[70,79,158],"unbiased":[72,157],"and":[73,122,186,205],"surprisingly":[74],"covariance":[76],"also":[80],"has":[81],"closed":[83],"form:":[84],"It":[85],"equals":[86],"specific":[88],"factor":[89],"times":[90],"$X^{+\\top}X^+$.":[91],"Pseudo":[92],"plays":[94],"an":[95,156,195],"important":[96],"part":[97],"in":[98],"solving":[99],"linear":[101,183],"squares":[103,185],"problem,":[104],"where":[105],"we":[106,123,135,142],"try":[107],"predict":[109],"label":[111],"for":[112,129,151,163,197,206,209],"each":[113],"column":[114,170],"$X$.":[116,138],"assume":[118],"labels":[119,128],"are":[120,124],"expensive":[121],"only":[125],"given":[126],"small":[131],"sample":[136],"from":[137],"Using":[139],"our":[140,191],"methods":[141,192],"weight":[146],"vector":[147],"solution":[150,162,217],"sub":[153],"problem":[154,166],"optimal":[161],"whole":[165],"all":[169,219],"labels.":[171],"believe":[173],"these":[175],"new":[176],"formulas":[177],"establish":[178],"fundamental":[180],"connection":[181],"between":[182],"sampling.":[188],"use":[190],"obtain":[194],"algorithm":[196],"sampling":[199],"faster":[202],"state-of-the-art":[204],"obtaining":[207],"bounds":[208],"total":[211],"loss":[212],"estimated":[215],"least-squares":[216],"labeled":[220],"columns.":[221]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2963324739","counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2019-07-30T00:00:00"}
