{"id":"https://openalex.org/W7213602748","doi":"https://doi.org/10.48550/arxiv.2609.20733","title":"Robust Multi-Task Learning for Principal Component Analysis","display_name":"Robust Multi-Task Learning for Principal Component Analysis","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213602748","doi":"https://doi.org/10.48550/arxiv.2609.20733"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.20733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20733","pdf_url":"https://arxiv.org/pdf/2609.20733","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2609.20733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101573421","display_name":"Dali Liu","orcid":"https://orcid.org/0000-0002-8560-1563","observed_orcids":["https://orcid.org/0000-0002-8560-1563"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003315201","display_name":"Haolei Weng","orcid":"https://orcid.org/0000-0002-9879-7841","observed_orcids":["https://orcid.org/0000-0002-9879-7841"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Haolei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.47609999775886536,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.47609999775886536,"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/T13141","display_name":"Statistical Methods and Applications","score":0.2660999894142151,"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/T10136","display_name":"Statistical Methods and Inference","score":0.1469999998807907,"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/multi-task-learning","display_name":"multi-task learning","score":0.7419999837875366},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.9769999980926514},{"id":"https://openalex.org/keywords/robust-estimation","display_name":"robust estimation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/non-asymptotic-convergence-rates","display_name":"non-asymptotic convergence rates","score":0.8650000095367432},{"id":"https://openalex.org/keywords/minimax-optimality","display_name":"minimax optimality","score":0.8370000123977661}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.798799991607666},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6718000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.564300000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.4629000127315521},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44589999318122864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41029998660087585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.364300012588501},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C71176878","wikidata":"https://www.wikidata.org/wiki/Q17014987","display_name":"Functional principal component analysis","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.20733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20733","pdf_url":"https://arxiv.org/pdf/2609.20733","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.20733","doi":"https://doi.org/10.48550/arxiv.2609.20733","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20733","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:2609.20733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20733","pdf_url":"https://arxiv.org/pdf/2609.20733","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/W7213602748.pdf","grobid_xml":"https://content.openalex.org/works/W7213602748.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2902113386","https://openalex.org/W4392780972","https://openalex.org/W4405312602","https://openalex.org/W4406548272","https://openalex.org/W4409419476","https://openalex.org/W4414769647","https://openalex.org/W4414856727","https://openalex.org/W4415137833","https://openalex.org/W7161686678","https://openalex.org/W7166669347","https://openalex.org/W7167610005","https://openalex.org/W7169837051"],"related_works":["https://openalex.org/W3126428072","https://openalex.org/W2542363056","https://openalex.org/W2572208444","https://openalex.org/W4372272938","https://openalex.org/W7161686678","https://openalex.org/W3209183255","https://openalex.org/W3206388874","https://openalex.org/W4414769647","https://openalex.org/W2032612424","https://openalex.org/W4389816923"],"abstract_inverted_index":{"Principal":[0],"component":[1],"analysis":[2],"(PCA)":[3],"is":[4],"a":[5,78,114],"fundamental":[6],"tool":[7],"for":[8],"learning":[9],"low-dimensional":[10],"structure":[11,49],"from":[12,19,37],"high-dimensional":[13],"data.":[14],"When":[15],"data":[16],"are":[17],"collected":[18],"multiple":[20],"sources,":[21],"the":[22,70,84,88,100,104,108,127,130],"underlying":[23],"task":[24],"distributions":[25],"may":[26],"exhibit":[27],"unknown":[28],"degrees":[29],"of":[30,80,83,91,103,110,129],"similarity,":[31],"with":[32],"some":[33],"tasks":[34,51],"potentially":[35],"arising":[36],"arbitrary":[38],"distributions.":[39],"We":[40,62],"propose":[41],"new":[42],"multi-task":[43,119],"PCA":[44],"procedures":[45,72,85],"that":[46,69],"exploit":[47],"similarity":[48],"across":[50],"to":[52,59],"improve":[53],"eigenspace":[54],"estimation":[55,105],"while":[56],"remaining":[57],"robust":[58,118],"outlier":[60,111],"tasks.":[61],"establish":[63],"non-asymptotic":[64],"convergence":[65],"rates":[66,76],"and":[67,94,97,123],"show":[68],"proposed":[71,131],"attain":[73],"minimax":[74],"optimal":[75,101],"in":[77,117],"range":[79],"regimes.":[81],"One":[82],"builds":[86],"on":[87,107],"matrix-depth":[89],"notion":[90],"Chen,":[92],"Gao,":[93],"Ren":[95],"(2018)":[96],"can":[98],"achieve":[99],"dependence":[102],"error":[106],"proportion":[109],"tasks,":[112],"addressing":[113],"key":[115],"challenge":[116],"learning.":[120],"Extensive":[121],"simulations":[122],"real-data":[124],"analyses":[125],"demonstrate":[126],"effectiveness":[128],"methods.":[132]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-19T00:00:00"}