{"id":"https://openalex.org/W7166667819","doi":"https://doi.org/10.48550/arxiv.2606.30230","title":"A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems","display_name":"A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166667819","doi":"https://doi.org/10.48550/arxiv.2606.30230"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.30230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30230","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.2606.30230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117571307","display_name":"Floor van Maarschalkerwaart","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van Maarschalkerwaart, Floor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139635487","display_name":"Subhadip Mukherjee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherjee, Subhadip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139647209","display_name":"Christoph Brune","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brune, Christoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139665638","display_name":"Marcello Carioni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carioni, Marcello","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":0.2506999969482422,"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":0.2506999969482422,"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":0.23000000417232513,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.055399999022483826,"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/interpretability","display_name":"Interpretability","score":0.6177999973297119},{"id":"https://openalex.org/keywords/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.5839999914169312},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.5752999782562256},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.47859999537467957},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.42480000853538513},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.36640000343322754},{"id":"https://openalex.org/keywords/strong-duality","display_name":"Strong duality","score":0.36320000886917114},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3544999957084656}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6492000222206116},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C152442038","wikidata":"https://www.wikidata.org/wiki/Q2778212","display_name":"Tikhonov regularization","level":3,"score":0.5839999914169312},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4968999922275543},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C163863214","wikidata":"https://www.wikidata.org/wiki/Q7624553","display_name":"Strong duality","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3544999957084656},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.287200003862381},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2653999924659729},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.30230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30230","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.2606.30230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30230","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learned":[0],"reconstruction":[1,96,177,196],"operators":[2,97],"for":[3,139,149,187],"inverse":[4],"problems":[5],"are":[6],"typically":[7],"trained":[8],"under":[9],"a":[10,42,71,131,229],"fixed":[11],"noise":[12,121,127],"model,":[13],"and":[14,61,120,143,155,179,194,201,206,227],"generalize":[15],"poorly":[16],"when":[17],"the":[18,24,38,51,63,66,77,87,117,152,172,176,210,213,221,225],"distribution":[19,40,54],"during":[20,27],"testing":[21],"differs":[22],"from":[23],"one":[25],"assumed":[26],"training.":[28],"Distributionally":[29],"robust":[30,100],"optimization":[31],"(DRO)":[32],"addresses":[33],"this":[34,140],"by":[35],"optimizing":[36],"against":[37],"worst-case":[39,164],"within":[41],"prescribed":[43],"ambiguity":[44,78],"set,":[45],"but":[46],"standard":[47,185,204],"Wasserstein":[48],"DRO":[49,73,186,205],"perturbs":[50],"full":[52],"joint":[53],"uniformly,":[55],"which":[56,76],"can":[57],"be":[58],"overly":[59],"conservative":[60,182],"ignores":[62],"physics":[64],"of":[65,175,224,232],"measurement":[67],"process.":[68,89],"We":[69,135],"develop":[70],"structured":[72,83],"framework":[74,113],"in":[75,116,151],"set":[79],"is":[80,161,180],"restricted":[81],"to":[82,93,101,107,184],"perturbations":[84,106,150],"aligned":[85],"with":[86],"data-acquisition":[88],"This":[90],"allows":[91],"us":[92],"learn":[94],"data-driven":[95,230],"that":[98,167],"remain":[99],"distributional":[102],"shifts.":[103],"By":[104],"constraining":[105],"subsets":[108],"such":[109],"as":[110,130],"$P(Y|X)$,":[111],"our":[112],"models":[114],"uncertainty":[115],"forward":[118,133],"operator":[119,215],"model":[122,128],"more":[123],"faithfully,":[124],"accommodating":[125],"any":[126],"expressible":[129],"stochastic":[132],"operator.":[134],"establish":[136],"strong":[137],"duality":[138],"general":[141],"formulation":[142],"derive":[144],"explicit":[145,163],"finite-dimensional":[146],"dual":[147],"representations":[148],"joint,":[153],"marginal,":[154],"conditional":[156],"distributions.":[157],"A":[158],"central":[159],"result":[160],"an":[162],"risk":[165],"bound":[166],"induces":[168],"Tikhonov":[169],"regularization":[170],"on":[171,192],"Lipschitz":[173],"constant":[174],"operator,":[178],"less":[181],"relative":[183],"well-posed":[188],"problems.":[189],"Numerical":[190],"experiments":[191],"deblurring":[193],"sinogram-to-CT":[195],"demonstrate":[197],"improved":[198],"robustness,":[199],"stability,":[200],"interpretability":[202],"over":[203],"MSE":[207],"baselines.":[208],"In":[209],"linear":[211],"setting,":[212],"learned":[214],"becomes":[216],"effectively":[217],"low-rank,":[218],"truncating":[219],"at":[220],"intrinsic":[222],"dimension":[223],"data":[226],"recovering":[228],"analogue":[231],"truncated-SVD":[233],"regularization.":[234]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}