{"id":"https://openalex.org/W7164911218","doi":"https://doi.org/10.48550/arxiv.2606.16045","title":"Active Learning with Low-Rank Structure for Data Selection","display_name":"Active Learning with Low-Rank Structure for Data Selection","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164911218","doi":"https://doi.org/10.48550/arxiv.2606.16045"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.16045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.16045","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138745225","display_name":"Vincent Cohen-Addad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cohen-Addad, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120364085","display_name":"Sasidhar Kunapuli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunapuli, Sasidhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127829360","display_name":"Vahab Mirrokni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirrokni, Vahab","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138721880","display_name":"Mahdi Nikdan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikdan, Mahdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138702631","display_name":"David P. Woodruff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Woodruff, David P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138757592","display_name":"Samson Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Samson","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":false,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4553000032901764,"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":0.4553000032901764,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.25450000166893005,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.07119999825954437,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6011999845504761},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5995000004768372},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5473999977111816},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.45190000534057617},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.44589999318122864},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.39570000767707825},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.3560999929904938}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4964999854564667},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47119998931884766},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4505000114440918},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.44589999318122864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.16045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.16045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,122],"the":[1,5,39,86,89,141,156,195,199,217,223],"data":[2,15,40,55,71,129,157,189,243],"selection":[3,72,130,146,244],"problem,":[4],"objective":[6],"is":[7,112,178],"to":[8,20,53,180,208],"choose":[9],"a":[10,23,70,127,182,203,237],"small,":[11],"representative":[12],"subset":[13,145,184],"of":[14,38,143,155,171,185,222,239],"that":[16,88,95,111,176,235],"can":[17,50,96,163],"be":[18,51,97,164],"used":[19,52],"efficiently":[21],"train":[22],"machine":[24],"learning":[25],"model.":[26],"Sener":[27],"and":[28,41,78,136,147],"Savarese":[29],"[ICLR":[30],"2018]":[31],"showed":[32],"that,":[33],"given":[34],"an":[35,152,209],"embedding":[36,153,224],"representation":[37,154],"suitable":[42],"geometric":[43,93],"assumptions,":[44],"heuristics":[45],"based":[46,74,132,252],"on":[47,75,85,133,236,253],"$k$-center":[48],"clustering":[49,77],"perform":[54],"selection.":[56],"This":[57],"perspective":[58],"was":[59],"further":[60],"explored":[61],"by":[62,100,115],"Axiotis":[63],"et.":[64],"al.":[65],"[ICML":[66],"2024],":[67],"who":[68],"proposed":[69],"approach":[73,245],"$k$-means":[76],"sensitivity":[79,258],"sampling.":[80,259],"However,":[81],"these":[82,228],"methods":[83],"rely":[84],"assumption":[87],"dataset":[90,201],"exhibits":[91],"intrinsic":[92],"structure":[94,110],"effectively":[98],"captured":[99],"clustering,":[101],"whereas":[102],"many":[103],"modern":[104],"datasets":[105],"instead":[106],"possess":[107],"global":[108],"algebraic":[109,167],"better":[113],"exploited":[114],"low-rank":[116,134],"approximation":[117,135,220],"or":[118,168,256],"principal":[119],"component":[120],"analysis.":[121],"this":[123],"paper,":[124],"we":[125,174],"introduce":[126],"new":[128],"framework":[131],"residual-based":[137],"sampling,":[138],"formulated":[139],"through":[140],"lens":[142],"row":[144],"loss-preserving":[148],"coreset":[149],"construction.":[150],"Given":[151],"satisfying":[158],"mild":[159],"regularity":[160],"conditions,":[161],"which":[162],"interpreted":[165],"as":[166],"angular":[169],"notions":[170],"Lipschitz":[172],"continuity,":[173],"show":[175],"it":[177],"possible":[179],"select":[181],"weighted":[183],"$\\tilde{O}\\left(k":[186],"+":[187],"\\frac{1}{\\varepsilon^2}\\right)$":[188],"points":[190],"whose":[191],"average":[192,196],"loss":[193,197],"approximates":[194],"over":[198,249],"full":[200],"within":[202],"$(1+\\varepsilon)$":[204],"relative":[205],"error,":[206],"up":[207],"additive":[210],"$\\varepsilon":[211],"\u03a6_k$":[212],"term,":[213],"where":[214],"$\u03a6_k$":[215],"denotes":[216],"optimal":[218],"rank-$k$":[219],"cost":[221],"matrix.":[225],"We":[226],"complement":[227],"theoretical":[229],"guarantees":[230],"with":[231],"empirical":[232],"evaluations,":[233],"demonstrating":[234],"range":[238],"real-world":[240],"datasets,":[241],"our":[242],"achieves":[246],"improved":[247],"performance":[248],"prior":[250],"strategies":[251],"uniform":[254],"sampling":[255],"clustering-based":[257]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}