{"id":"https://openalex.org/W7161557956","doi":"https://doi.org/10.48550/arxiv.2605.15789","title":"Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagation","display_name":"Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagation","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161557956","doi":"https://doi.org/10.48550/arxiv.2605.15789"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15789","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":null,"license_id":null,"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.2605.15789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136402415","display_name":"Ruirui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ruirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136399752","display_name":"Xuejie Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Xuejie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136414527","display_name":"Yiping Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yiping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064709709","display_name":"Hui Ren","orcid":"https://orcid.org/0000-0001-8366-3317"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Hui","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5586000084877014,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5586000084877014,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.06930000334978104,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.050599999725818634,"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/interval","display_name":"Interval (graph theory)","score":0.564300000667572},{"id":"https://openalex.org/keywords/conservatism","display_name":"Conservatism","score":0.5616999864578247},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4918999969959259},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.48249998688697815},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45010000467300415},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.430400013923645},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4284000098705292},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.41769999265670776},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C96640997","wikidata":"https://www.wikidata.org/wiki/Q5163004","display_name":"Conservatism","level":3,"score":0.5616999864578247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4952999949455261},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48069998621940613},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4004000127315521},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C205167067","wikidata":"https://www.wikidata.org/wiki/Q3300636","display_name":"Interval estimation","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C191252586","wikidata":"https://www.wikidata.org/wiki/Q1671453","display_name":"Interval arithmetic","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15789","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15789","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":null,"license_id":null,"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":{"Uncertainty":[0],"quantification":[1],"is":[2,222],"essential":[3],"in":[4,218,235],"safety-critical":[5],"settings--from":[6],"autonomous":[7],"driving":[8],"to":[9,90,92,105,226],"aviation,":[10,58],"finance,":[11],"and":[12,88,110,153,160,183,187,192,198,217,224],"health--where":[13],"decisions":[14],"must":[15],"rely":[16],"on":[17,114,127,156,161,189,213],"conservative":[18,67,151],"bounds":[19,149,209],"rather":[20],"than":[21,172],"point":[22],"estimates.":[23],"Predictor-level":[24],"intervals":[25,44],"(e.g.,":[26],"from":[27],"quantile":[28,117],"regression,":[29],"conformal":[30],"prediction,":[31],"variance":[32],"networks,":[33],"or":[34,54],"Bayesian":[35],"models)":[36],"generally":[37],"do":[38],"not":[39,46],"compose:":[40],"adding":[41],"two":[42],"per-variable":[43],"need":[45],"yield":[47],"a":[48,66,97,115,128,144,177],"valid":[49],"interval":[50,164],"for":[51],"their":[52],"sum":[53],"preserve":[55],"coverage.":[56],"In":[57],"Gaussian":[59,68,108],"overbounding":[60,132],"replaces":[61],"complex":[62],"error":[63],"distributions":[64],"with":[65,143],"whose":[69],"tails":[70],"dominate":[71],"the":[72,157,162,205,214],"truth,":[73],"so":[74],"conservatism":[75,113,126,182,212],"propagates":[76],"through":[77],"linear":[78],"operations.":[79],"Yet":[80],"classical":[81],"overbounds":[82],"are":[83],"global,":[84],"often":[85],"overly":[86],"conservative,":[87,231],"hard":[89],"adapt":[91],"feature-conditioned":[93,232],"errors.":[94,201],"We":[95,175],"propose":[96],"unified":[98],"learning":[99,227],"framework":[100,221],"that":[101,229],"trains":[102],"neural":[103],"networks":[104],"produce":[106],"context-aware":[107],"overbounds--mean":[109],"scale--with":[111],"provable":[112],"finite":[116],"grid":[118,216],"and,":[119],"under":[120],"three":[121],"explicit":[122],"regularity":[123],"assumptions,":[124],"continuous-tail":[125],"certified":[129,163],"interval.":[130],"Our":[131],"loss":[133],"enforces":[134],"conservativeness":[135],"at":[136],"selected":[137],"quantiles":[138],"while":[139,168,210],"penalizing":[140],"distributional":[141],"distance":[142],"Wasserstein-style":[145],"term.":[146],"The":[147,220],"learned":[148],"support":[150],"linear-combination":[152],"convolution":[154],"analysis":[155,179],"enforced":[158,215],"grid,":[159],"when":[165],"assumptions":[166],"hold,":[167],"being":[169],"less":[170],"redundant":[171],"traditional":[173],"methods.":[174],"provide":[176],"scoped":[178],"of":[180],"discrete-to-continuous":[181],"compact-domain":[184],"objective":[185],"regularity,":[186],"validate":[188],"synthetic":[190],"data":[191],"real-world":[193],"datasets,":[194],"including":[195],"multipath,":[196],"ionospheric,":[197],"tropospheric":[199],"residual":[200],"Across":[202],"these":[203],"settings,":[204],"method":[206],"yields":[207],"tighter":[208],"maintaining":[211],"experiments.":[219],"modality-agnostic":[223],"applicable":[225],"systems":[228],"require":[230],"uncertainty":[233],"estimates":[234],"dynamic":[236],"environments.":[237]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}