{"id":"https://openalex.org/W7128636042","doi":"https://doi.org/10.48550/arxiv.2602.09639","title":"Blind denoising diffusion models and the blessings of dimensionality","display_name":"Blind denoising diffusion models and the blessings of dimensionality","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128636042","doi":"https://doi.org/10.48550/arxiv.2602.09639"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.09639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.09639","pdf_url":"https://arxiv.org/pdf/2602.09639","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.09639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056405277","display_name":"Zahra Kadkhodaie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107338","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kadkhodaie, Zahra","raw_affiliation_strings":["Flatiron Institute , Simons Foundation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flatiron Institute , Simons Foundation","institution_ids":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014231683","display_name":"Aram-Alexandre Pooladian","orcid":"https://orcid.org/0000-0002-9553-8852","observed_orcids":["https://orcid.org/0000-0002-9553-8852"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pooladian, Aram-Alexandre","raw_affiliation_strings":["Foundations of Data Science , Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundations of Data Science , Yale University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052571538","display_name":"Sinho Chewi","orcid":"https://orcid.org/0000-0003-2701-0703","observed_orcids":["https://orcid.org/0000-0003-2701-0703"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chewi, Sinho","raw_affiliation_strings":["Department of Statistics and Data Science , Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080476548","display_name":"Eero P. Simoncelli","orcid":"https://orcid.org/0000-0002-1206-527X","observed_orcids":["https://orcid.org/0000-0002-1206-527X"]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I4210107338","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simoncelli, Eero","raw_affiliation_strings":["Ctr. for Neural Science & Courant Institute , New York University","Flatiron Institute , Simons Foundation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ctr. for Neural Science & Courant Institute , New York University","institution_ids":["https://openalex.org/I36672615"]},{"raw_affiliation_string":"Flatiron Institute , Simons Foundation","institution_ids":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.44359999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.44359999895095825,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.20509999990463257,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1046999990940094,"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/denoising-diffusion-probabilistic-models","display_name":"denoising diffusion probabilistic models","score":0.9860000014305115},{"id":"https://openalex.org/keywords/noise-level-estimation","display_name":"noise level estimation","score":0.6259999871253967},{"id":"https://openalex.org/keywords/intrinsic-dimension","display_name":"intrinsic dimension","score":0.8610000014305115},{"id":"https://openalex.org/keywords/sampling-algorithms","display_name":"sampling algorithms","score":0.5109999775886536},{"id":"https://openalex.org/keywords/noise-schedule","display_name":"noise schedule","score":0.5360000133514404},{"id":"https://openalex.org/keywords/density-estimation","display_name":"density estimation","score":0.6299999952316284},{"id":"https://openalex.org/keywords/bayesian-estimation","display_name":"Bayesian estimation","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7350999712944031},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5328999757766724},{"id":"https://openalex.org/C200378446","wikidata":"https://www.wikidata.org/wiki/Q4147391","display_name":"Gradient noise","level":5,"score":0.5307999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C182163834","wikidata":"https://www.wikidata.org/wiki/Q2926529","display_name":"Value noise","level":5,"score":0.47769999504089355},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.43799999356269836},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41780000925064087},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41110000014305115},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C98385598","wikidata":"https://www.wikidata.org/wiki/Q1339385","display_name":"Empirical distribution function","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.09639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.09639","pdf_url":"https://arxiv.org/pdf/2602.09639","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.2602.09639","doi":"https://doi.org/10.48550/arxiv.2602.09639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.09639","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:2602.09639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.09639","pdf_url":"https://arxiv.org/pdf/2602.09639","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":[{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320319356","display_name":"Flatiron Health","ror":"https://ror.org/0508h6p74"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128636042.pdf","grobid_xml":"https://content.openalex.org/works/W7128636042.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7135205807","https://openalex.org/W3193411928","https://openalex.org/W4380136171","https://openalex.org/W4320184687","https://openalex.org/W4377009988","https://openalex.org/W4400105171","https://openalex.org/W4417308587","https://openalex.org/W4381826788","https://openalex.org/W3122887982","https://openalex.org/W4406779567"],"abstract_inverted_index":{"Denoising":[0],"diffusion":[1,64],"models":[2],"(DDMs)":[3],"are":[4],"state-of-the-art":[5],"methods":[6],"for":[7,50,61,89],"learning":[8],"densities":[9],"from":[10,135],"data":[11,114],"across":[12],"numerous":[13],"domains,":[14],"yet":[15],"many":[16],"aspects":[17],"of":[18,69,98,107,111,127,131,143,151,159],"the":[19,72,79,87,90,96,112,118,125,128,149,157],"training":[20,83],"and":[21,43],"sampling":[22,102],"pipeline":[23],"remain":[24],"poorly":[25],"understood.":[26],"In":[27],"particular,":[28],"noise":[29,37,48,73,133],"conditioning":[30],"requires":[31],"practitioners":[32],"to":[33,44,117,153],"incorporate":[34],"contrived":[35],"unprincipled":[36],"embeddings":[38],"into":[39,78],"neural":[40,80],"network":[41,81],"architectures":[42],"use":[45],"ad":[46],"hoc":[47],"schedules":[49],"sampling.":[51],"To":[52],"address":[53],"these":[54],"drawbacks,":[55],"we":[56],"provide":[57],"a":[58,67,101,136],"complete":[59],"theory":[60],"\\emph{blind":[62],"denoising":[63],"models}":[65],"(BDDMs):":[66],"variant":[68],"DDMs":[70],"where":[71],"amplitude":[74],"is":[75,164],"not":[76],"passed":[77],"during":[82],"or":[84],"sampling,":[85],"obviating":[86],"need":[88],"aforementioned":[91],"design":[92],"choices.":[93],"We":[94,146],"justify":[95],"correctness":[97],"BDDMs":[99,152],"as":[100],"algorithm":[103],"under":[104],"an":[105,160],"assumption":[106,122],"low":[108],"intrinsic":[109],"dimensionality":[110],"underlying":[113],"distribution":[115],"relative":[116],"ambient":[119],"dimension.":[120],"This":[121],"arises":[123],"through":[124],"introduction":[126],"Bayesian":[129],"problem":[130],"estimating":[132],"levels":[134],"single":[137],"noisy":[138],"sample,":[139],"which":[140,163],"might":[141],"be":[142],"independent":[144],"interest.":[145],"empirically":[147],"compare":[148],"performance":[150],"standard":[154],"DDMs,":[155],"showcasing":[156],"benefits":[158],"\\emph{adaptive}":[161],"scheme":[162],"rigorously":[165],"justified":[166],"by":[167],"our":[168],"analysis.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-02-12T00:00:00"}