{"id":"https://openalex.org/W7213326967","doi":"https://doi.org/10.48550/arxiv.2609.15111","title":"Low-Rank Denoising for Predict-then-Optimize","display_name":"Low-Rank Denoising for Predict-then-Optimize","publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213326967","doi":"https://doi.org/10.48550/arxiv.2609.15111"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.15111","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15111","pdf_url":"https://arxiv.org/pdf/2609.15111","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/2609.15111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151769597","display_name":"Henry Aldridge-Krawciw","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aldridge-Krawciw, Henry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5151796416","display_name":"Irene Aldridge","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aldridge, Irene","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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.7935000061988831,"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":0.7935000061988831,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.09929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.03180000185966492,"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/predict-then-optimize","display_name":"predict-then-optimize","score":0.9399999976158142},{"id":"https://openalex.org/keywords/shortest-path","display_name":"shortest path","score":0.6579999923706055},{"id":"https://openalex.org/keywords/subspace-projection","display_name":"subspace projection","score":0.6330000162124634},{"id":"https://openalex.org/keywords/sample-mean","display_name":"sample mean","score":0.32600000500679016},{"id":"https://openalex.org/keywords/incoherence","display_name":"incoherence","score":0.6230000257492065}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5152000188827515},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4636000096797943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4392000138759613},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C169756996","wikidata":"https://www.wikidata.org/wiki/Q194919","display_name":"Eigendecomposition of a matrix","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.15111","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15111","pdf_url":"https://arxiv.org/pdf/2609.15111","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.2609.15111","doi":"https://doi.org/10.48550/arxiv.2609.15111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.15111","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:2609.15111","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15111","pdf_url":"https://arxiv.org/pdf/2609.15111","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213326967.pdf","grobid_xml":"https://content.openalex.org/works/W7213326967.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7161237416"],"related_works":["https://openalex.org/W7213302280","https://openalex.org/W7213447377","https://openalex.org/W6949426327","https://openalex.org/W2118182581","https://openalex.org/W2125616269","https://openalex.org/W4297817366","https://openalex.org/W3101873331","https://openalex.org/W7208120189","https://openalex.org/W7099303559","https://openalex.org/W2557768975"],"abstract_inverted_index":{"A":[0,152,170],"shortest-path":[1],"decision":[2],"is":[3,72,82,91,116,123,131],"often":[4],"made":[5],"from":[6,173],"edge":[7],"costs":[8,88],"that":[9,42,130,156],"are":[10],"only":[11,132],"observed":[12],"through":[13],"noisy":[14,175],"samples,":[15],"such":[16],"as":[17],"the":[18,25,38,73,83,86,92,99,102,117,143,157,166],"average":[19,145],"of":[20,29,55,76,85,104,119,159],"$m$":[21],"simulation":[22],"replications.":[23],"When":[24],"mean":[26,52,107],"cost":[27],"vectors":[28],"different":[30],"instances":[31,176],"lie":[32],"near":[33],"a":[34,62,66,96,105,109,128,161],"$k$-dimensional":[35],"subspace,":[36],"projecting":[37],"averaged":[39],"sample":[40,106],"onto":[41],"subspace":[43],"should":[44],"remove":[45],"noise.":[46],"We":[47],"make":[48],"this":[49],"precise.":[50],"The":[51,69],"squared":[53],"error":[54,103,140],"any":[56],"projection":[57,100,137],"estimator":[58],"splits":[59],"exactly":[60],"into":[61],"variance":[63],"term":[64],"and":[65,89,121,142],"bias":[67],"term.":[68,182],"best":[70],"projector":[71,171],"positive":[74],"eigenspace":[75],"$\u03a3_c":[77],"-":[78],"D/m$,":[79],"where":[80,114],"$\u03a3_c$":[81],"covariance":[84],"true":[87],"$D$":[90],"noise":[93],"covariance.":[94],"For":[95,127],"rank-$k$":[97,136],"signal,":[98],"has":[101,138],"with":[108],"factor":[110],"$d/(\u03bck)$":[111],"more":[112],"replications,":[113],"$d$":[115],"number":[118],"edges":[120],"$\u03bc$":[122],"an":[124,139,148,180],"incoherence":[125],"constant.":[126],"signal":[129],"approximately":[133],"low-rank,":[134],"every":[135],"floor,":[141],"plain":[144],"wins":[146],"beyond":[147],"explicit":[149],"replication":[150],"count.":[151],"margin":[153],"bound":[154],"shows":[155],"chance":[158],"choosing":[160],"suboptimal":[162],"path":[163],"falls":[164],"at":[165,178],"same":[167],"improved":[168],"rate.":[169],"learned":[172],"$n$":[174],"loses":[177],"most":[179],"$O(d/n)$":[181]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-16T00:00:00"}