{"id":"https://openalex.org/W4387322947","doi":"https://doi.org/10.48550/arxiv.2310.01326","title":"Optimal Estimator for Linear Regression with Shuffled Labels","display_name":"Optimal Estimator for Linear Regression with Shuffled Labels","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4387322947","doi":"https://doi.org/10.48550/arxiv.2310.01326"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.01326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01326","pdf_url":"https://arxiv.org/pdf/2310.01326","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2310.01326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100438428","display_name":"Hang Zhang","orcid":"https://orcid.org/0000-0001-6892-2624","observed_orcids":["https://orcid.org/0000-0001-6892-2624"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hang","raw_affiliation_strings":["Cognitive Computing Lab Baidu Research 10900 NE 8th St. Bellevue , WA 98004 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research 10900 NE 8th St. Bellevue , WA 98004 , USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435527","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773","observed_orcids":["https://orcid.org/0000-0002-8515-7773","https://orcid.org/0000-0002-5979-8868","https://orcid.org/0000-0002-7985-8477","https://orcid.org/0000-0002-1503-0240","https://orcid.org/0000-0002-8391-6510","https://orcid.org/0000-0001-8285-8921","https://orcid.org/0000-0003-4725-4553"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ping","raw_affiliation_strings":["Cognitive Computing Lab Baidu Research 10900 NE 8th St. Bellevue , WA 98004 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research 10900 NE 8th St. Bellevue , WA 98004 , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.00839999970048666,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.005200000014156103,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.7760000228881836},{"id":"https://openalex.org/keywords/matrix-completion","display_name":"matrix completion","score":0.40700000524520874},{"id":"https://openalex.org/keywords/low-rank-matrix-estimation","display_name":"low-rank matrix estimation","score":0.6019999980926514},{"id":"https://openalex.org/keywords/one-step-estimator","display_name":"one-step estimator","score":0.597000002861023},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"signal-to-noise ratio","score":0.4749999940395355},{"id":"https://openalex.org/keywords/stable-rank","display_name":"stable rank","score":0.746999979019165},{"id":"https://openalex.org/keywords/missing-labels","display_name":"missing labels","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.7178785800933838},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.5022590160369873},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4978959560394287},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45841217041015625},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4468822181224823},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4325036406517029},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4182603657245636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41489654779434204},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1739586889743805},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07787075638771057},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.01326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01326","pdf_url":"https://arxiv.org/pdf/2310.01326","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.01326","doi":"https://doi.org/10.48550/arxiv.2310.01326","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.01326","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.01326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01326","pdf_url":"https://arxiv.org/pdf/2310.01326","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W4387322947.pdf","grobid_xml":"https://content.openalex.org/works/W4387322947.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2240646096","https://openalex.org/W2610882944","https://openalex.org/W3205516812","https://openalex.org/W4225598812"],"related_works":["https://openalex.org/W2610882944","https://openalex.org/W2768422320","https://openalex.org/W2938624639","https://openalex.org/W4401692397","https://openalex.org/W2487808988","https://openalex.org/W4294789348","https://openalex.org/W7126345064","https://openalex.org/W3196559251","https://openalex.org/W4300980645","https://openalex.org/W3214659106"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"the":[3,55,73,94,109,128,133,152,164,173,185,198,205,214],"task":[4],"of":[5,66,112,201],"linear":[6,114],"regression":[7],"with":[8],"shuffled":[9],"labels,":[10],"i.e.,":[11],"$\\mathbf":[12,24,48,75,80,202],"Y":[13,25],"=":[14],"\\mathbf":[15,18,21,30,36,41,91],"\u03a0\\mathbf":[16],"X":[17],"B":[19,42],"+":[20,102],"W$,":[22],"where":[23],"\\in":[26,32,43],"\\mathbb":[27,33,38,44,50],"R^{n\\times":[28,34,39,51],"m},":[29],"Pi":[31],"n},":[35],"X\\in":[37],"p},":[40],"R^{p\\times":[45],"m}$,":[46,52],"and":[47,68,77,119,144,147,176,194],"W\\in":[49],"respectively,":[53],"represent":[54],"sensing":[56,63,70,78],"results,":[57],"(unknown":[58],"or":[59],"missing)":[60],"corresponding":[61],"information,":[62],"matrix,":[64],"signal":[65],"interest,":[67],"additive":[69],"noise.":[71],"Given":[72],"observation":[74],"Y$":[76],"matrix":[79],"X$,":[81],"we":[82,131,207],"propose":[83],"a":[84,113,120],"one-step":[85],"estimator":[86],"to":[87,212],"reconstruct":[88],"$(\\mathbf":[89],"\u03a0,":[90],"B)$.":[92],"From":[93,127],"computational":[95],"perspective,":[96,130],"our":[97],"estimator's":[98],"complexity":[99,111],"is":[100,105],"$O(n^3":[101],"np^2m)$,":[103],"which":[104],"no":[106],"greater":[107],"than":[108],"maximum":[110],"assignment":[115],"algorithm":[116,123],"(e.g.,":[117,124],"$O(n^3)$)":[118],"least":[121],"square":[122],"$O(np^2":[125],"m)$).":[126],"statistical":[129],"divide":[132],"minimum":[134],"$snr$":[135],"requirement":[136],"into":[137],"four":[138],"regimes,":[139],"e.g.,":[140],"unknown,":[141],"hard,":[142],"medium,":[143],"easy":[145,165],"regimes;":[146],"present":[148],"sufficient":[149],"conditions":[150],"for":[151],"correct":[153],"permutation":[154],"recovery":[155],"under":[156],"each":[157],"regime:":[158],"$(i)$":[159],"$snr":[160,168,178],"\\geq":[161,169,179],"\u03a9(1)$":[162],"in":[163,172,184],"regime;":[166,175],"$(ii)$":[167],"\u03a9(\\log":[170],"n)$":[171],"medium":[174],"$(iii)$":[177],"\u03a9((\\log":[180],"n)^{c_0}\\cdot":[181],"n^{{c_1}/{srank(\\mathbf":[182],"B)}})$":[183],"hard":[186],"regime":[187],"($c_0,":[188],"c_1$":[189],"are":[190],"some":[191],"positive":[192],"constants":[193],"$srank(\\mathbf":[195],"B)$":[196],"denotes":[197],"stable":[199],"rank":[200],"B$).":[203],"In":[204],"end,":[206],"also":[208],"provide":[209],"numerical":[210],"experiments":[211],"confirm":[213],"above":[215],"claims.":[216]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-04T00:00:00"}