{"id":"https://openalex.org/W7139965397","doi":"https://doi.org/10.48550/arxiv.2603.18483","title":"Precise Performance of Linear Denoisers in the Proportional Regime","display_name":"Precise Performance of Linear Denoisers in the Proportional Regime","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139965397","doi":"https://doi.org/10.48550/arxiv.2603.18483"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18483","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18483","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093219798","display_name":"Reza Ghane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghane, Reza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036629613","display_name":"Danil Akhtiamov","orcid":"https://orcid.org/0000-0002-9238-9636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akhtiamov, Danil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130247392","display_name":"Babak Hassibi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassibi, Babak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T10136","display_name":"Statistical Methods and Inference","score":0.3614000082015991,"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/T10136","display_name":"Statistical Methods and Inference","score":0.3614000082015991,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.10480000078678131,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.0851999968290329,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.8136000037193298},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.6306999921798706},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5440000295639038},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5263000130653381},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4765999913215637},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4530999958515167},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.439300000667572},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.3790999948978424},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.8136000037193298},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6136999726295471},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.542900025844574},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.439300000667572},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.325300008058548},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C139722471","wikidata":"https://www.wikidata.org/wiki/Q2619517","display_name":"Linear filter","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C15652857","wikidata":"https://www.wikidata.org/wiki/Q599016","display_name":"Wiener deconvolution","level":4,"score":0.296099990606308},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C60391097","wikidata":"https://www.wikidata.org/wiki/Q1056809","display_name":"Wiener process","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C41614226","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering problem","level":4,"score":0.2727999985218048},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18483","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18483","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,122,159],"the":[1,6,15,25,44,50,70,83,100,119,131,135,147,160,169,179,184,188,204,216,225],"present":[2],"paper":[3],"we":[4,60,62,106,112,124,167],"study":[5],"performance":[7],"of":[8,14,130,187],"linear":[9,115],"denoisers":[10],"for":[11,57,183],"noisy":[12,127],"data":[13,27,120,132],"form":[16,181],"$\\mathbf{x}":[17,21],"+":[18],"\\mathbf{z}$,":[19],"where":[20],"\\in":[22,67],"\\mathbb{R}^d$":[23,68],"is":[24,40,47],"desired":[26],"with":[28,137,140],"zero":[29],"mean":[30],"and":[31,35,85,145,223],"unknown":[32],"covariance":[33,45,141],"$\\mathbf\u03a3$,":[34],"$\\mathbf{z}":[36],"\\sim":[37],"\\mathcal{N}(0,":[38],"\\mathbf\u03a3_{\\mathbf{z}})$":[39],"additive":[41],"noise.":[42],"Since":[43],"$\\mathbf\u03a3$":[46,81],"not":[48],"known,":[49],"standard":[51,74],"Wiener":[52,92,218,227],"filter":[53,219,228],"cannot":[54],"be":[55,78],"employed":[56],"denoising.":[58],"Instead":[59],"assume":[61],"are":[63],"given":[64],"samples":[65,84,128,136],"$\\mathbf{x}_1,\\dots,\\mathbf{x}_n":[66],"from":[69,82,118,191],"true":[71],"distribution.":[72],"A":[73],"approach":[75,110],"would":[76],"then":[77],"to":[79,88,176,202],"estimate":[80],"use":[86,168],"it":[87],"construct":[89,126],"an":[90],"``empirical\"":[91,217],"filter.":[93],"However,":[94],"in":[95,103,155,220],"this":[96,192,195],"paper,":[97],"motivated":[98],"by":[99,133],"denoising":[101],"step":[102],"diffusion":[104],"models,":[105],"take":[107],"a":[108,114,156],"different":[109],"whereby":[111],"train":[113],"denoiser":[116,189,214],"$\\mathbf{W}$":[117,149],"itself.":[121],"particular,":[123],"synthetically":[125],"$\\hat{\\mathbf{x}}_i$":[129],"injecting":[134],"Gaussian":[138,172],"noise":[139],"$\\mathbf\u03a3_1":[142],"\\neq":[143],"\\mathbf\u03a3_{\\mathbf{z}}$":[144],"find":[146,178,203],"best":[148,205],"that":[150,212],"approximates":[151],"$\\mathbf{W}\\hat{\\mathbf{x}}_i":[152],"\\approx":[153],"\\mathbf{x}_i$":[154],"least-squares":[157],"sense.":[158],"proportional":[161],"regime":[162],"$\\frac{n}{d}":[163],"\\rightarrow":[164],"\u03ba>":[165],"1$":[166],"{\\it":[170],"Convex":[171],"Min-Max":[173],"Theorem":[174],"(CGMT)}":[175],"analytically":[177],"closed":[180],"expression":[182,196],"generalization":[185],"error":[186],"obtained":[190],"process.":[193],"Using":[194],"one":[197],"can":[198],"optimize":[199],"over":[200],"$\\mathbf\u03a3_1$":[201],"possible":[206],"denoiser.":[207],"Our":[208],"numerical":[209],"simulations":[210],"show":[211],"our":[213],"outperforms":[215],"many":[221],"scenarios":[222],"approaches":[224],"optimal":[226],"as":[229],"$\u03ba\\rightarrow\\infty$.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-21T00:00:00"}