{"id":"https://openalex.org/W7172273829","doi":"https://doi.org/10.48550/arxiv.2607.29525","title":"Physics Matters in PnP: Recovery Guarantees with the MMSE and NN Denoisers","display_name":"Physics Matters in PnP: Recovery Guarantees with the MMSE and NN Denoisers","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7172273829","doi":"https://doi.org/10.48550/arxiv.2607.29525"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.29525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29525","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,"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.2607.29525","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103147770","display_name":"Tobias Wolf","orcid":"https://orcid.org/0000-0002-2665-4219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolf, Tobias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144251171","display_name":"Jalal Fadili","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fadili, Jalal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144263320","display_name":"Jin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101393755","display_name":"Roy Y. He","orcid":"https://orcid.org/0009-0006-4690-4007"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Roy Y.","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":0.4431999921798706,"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":0.4431999921798706,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.24860000610351562,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.04610000178217888,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7218999862670898},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.7132999897003174},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5401999950408936},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41769999265670776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41350001096725464},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.412200003862381},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.7132999897003174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5412999987602234},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5016000270843506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43939998745918274},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.29525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29525","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,"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.2607.29525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29525","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,"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":{"We":[0,41,120],"investigate":[1],"the":[2,6,45,52,61,67,78,85,91,95,104,117,125,128,139],"forward-backward-splitting":[3],"version":[4],"of":[5,51,66,77,84,94,116],"Plug":[7],"and":[8,80,89,137],"Play":[9],"(PnP)":[10],"method":[11],"for":[12,32],"linear":[13,57],"ill-posed":[14],"problems":[15],"with":[16,36,55],"MMSE":[17,68,129],"estimators":[18,28],"as":[19],"denoisers.":[20],"In":[21],"contrast":[22],"to":[23,64,124],"existing":[24],"literature,":[25],"we":[26,73],"consider":[27],"which":[29],"are":[30],"specialized":[31],"(degenerate)":[33],"Gaussian":[34],"noise":[35,63],"possibly":[37],"non-diagonal":[38],"covariance":[39],"matrices.":[40],"further":[42],"deviate":[43],"from":[44],"classical":[46],"iteration":[47,86],"by":[48,133],"replacing":[49],"parts":[50],"descent":[53],"step":[54],"a":[56,110,134],"operator":[58],"that":[59,65,103,113],"relates":[60],"observation":[62],"estimator.":[69],"Under":[70],"mild":[71],"assumptions,":[72],"derive":[74,138],"several":[75],"properties":[76],"denoiser":[79,105,130],"prove":[81],"recovery":[82,141],"guarantees":[83],"both":[87],"pointwise":[88],"in":[90,109],"Wasserstein":[92],"distance":[93],"underlying":[96],"probability":[97],"distributions.":[98],"Crucially,":[99],"our":[100,122],"analysis":[101],"shows":[102],"cannot":[106],"be":[107],"chosen":[108],"physics-agnostic":[111],"way,":[112],"is,":[114],"independently":[115],"forward":[118],"model.":[119],"extend":[121],"results":[123],"case":[126],"where":[127],"is":[131],"parametrized":[132],"neural":[135],"network":[136],"corresponding":[140],"bounds.":[142]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2026-08-04T00:00:00"}