{"id":"https://openalex.org/W7164895415","doi":"https://doi.org/10.48550/arxiv.2606.17048","title":"Exact Posterior Score Estimation for Solving Linear Inverse Problems","display_name":"Exact Posterior Score Estimation for Solving Linear Inverse Problems","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164895415","doi":"https://doi.org/10.48550/arxiv.2606.17048"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17048","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.2606.17048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138737421","display_name":"Abbas Mammadov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mammadov, Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133584884","display_name":"Ozgur Kara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kara, Ozgur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009438864","display_name":"Kaan Oktay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oktay, Kaan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138741174","display_name":"Iskander Azangulov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azangulov, Iskander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089010304","display_name":"Adil Kaan Akan","orcid":"https://orcid.org/0000-0003-0022-7224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akan, Adil Kaan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006604581","display_name":"Hyungjin Chung","orcid":"https://orcid.org/0000-0003-3202-0893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Hyungjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002228469","display_name":"James M. Rehg","orcid":"https://orcid.org/0000-0003-1793-5462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rehg, James Matthew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138719065","display_name":"Yee Whye Teh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teh, Yee Whye","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5315999984741211,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5315999984741211,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11339999735355377,"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":0.03799999877810478,"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/posterior-probability","display_name":"Posterior probability","score":0.6679999828338623},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6585999727249146},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.527400016784668},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5218999981880188},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4828999936580658},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.43869999051094055},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.41659998893737793}],"concepts":[{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6679999828338623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6588000059127808},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6585999727249146},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46540001034736633},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C132878287","wikidata":"https://www.wikidata.org/wiki/Q1671727","display_name":"Inverse Gaussian distribution","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C76134657","wikidata":"https://www.wikidata.org/wiki/Q370634","display_name":"Generalized inverse","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25369998812675476},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17048","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.2606.17048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17048","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.793641209602356}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"and":[1,92,133,173,179,185],"flow-based":[2],"models":[3],"learn":[4],"powerful":[5],"data":[6],"priors":[7],"by":[8],"training":[9,123],"a":[10,22,52,62,99,121,143],"denoiser":[11,55,196],"to":[12,20,28,98],"reverse":[13],"Gaussian":[14,85,90],"corruption.":[15],"To":[16],"use":[17],"this":[18,114],"prior":[19,38],"solve":[21],"linear":[23,84,168],"inverse":[24,86,169],"problem,":[25],"one":[26],"needs":[27],"sample":[29],"from":[30,138,142],"the":[31,34,37,41,45,68,72,76,127,150,154],"posterior,":[32],"but":[33],"score":[35,79],"that":[36,66,94,125],"provides":[39],"is":[40],"unconditional":[42],"score,":[43],"not":[44],"posterior":[46,78,95,200],"score.":[47],"Existing":[48],"methods":[49],"either":[50],"steer":[51],"fixed":[53],"pretrained":[54,144],"with":[56,157],"approximate":[57],"measurement-matching":[58],"corrections,":[59],"or":[60,140,161],"train":[61],"conditional":[63],"restoration":[64],"model":[65],"abandons":[67],"denoising":[69,100,122],"structure":[70,129],"of":[71,130,193],"prior.":[73],"We":[74,112,163],"derive":[75],"exact":[77],"in":[80],"closed":[81],"form":[82],"for":[83],"problems":[87,170],"under":[88,107],"general":[89],"interpolants,":[91],"show":[93],"sampling":[96],"reduces":[97],"problem":[101],"at":[102],"an":[103,108,191],"operator-dependent":[104],"shifted":[105],"pivot":[106],"anisotropic":[109],"noise":[110],"covariance.":[111],"turn":[113],"identity":[115],"into":[116],"Exact":[117],"Posterior":[118],"Score":[119],"(EPS),":[120],"objective":[124],"preserves":[126],"input/output":[128],"standard":[131],"pretraining":[132],"can":[134],"therefore":[135],"be":[136],"trained":[137],"scratch":[139],"fine-tuned":[141],"denoiser.":[145],"At":[146],"inference,":[147],"EPS":[148,165],"uses":[149],"same":[151],"sampler":[152],"as":[153],"underlying":[155],"backbone,":[156],"no":[158],"likelihood":[159],"gradients":[160],"projections.":[162],"evaluate":[164],"on":[166,182],"five":[167],"across":[171],"FFHQ":[172],"ImageNet,":[174],"where":[175],"it":[176],"outperforms":[177],"training-free":[178],"training-based":[180],"baselines":[181],"fidelity,":[183],"perceptual,":[184],"distributional":[186],"metrics,":[187],"while":[188],"using":[189],"roughly":[190],"order":[192],"magnitude":[194],"fewer":[195],"evaluations":[197],"than":[198],"gradient-based":[199],"samplers.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}