{"id":"https://openalex.org/W7123351098","doi":"https://doi.org/10.1109/cdc57313.2025.11312354","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","display_name":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123351098","doi":"https://doi.org/10.1109/cdc57313.2025.11312354"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122897431","display_name":"Anne Somalwar","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anne Somalwar","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122859500","display_name":"Bruce D. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce D. Lee","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122895443","display_name":"George J. Pappas","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George J. Pappas","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052941508","display_name":"Nikolai Matni","orcid":"https://orcid.org/0000-0003-4936-3921"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolai Matni","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122897431"],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85840629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4878000020980835,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4878000020980835,"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":0.27079999446868896,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.043699998408555984,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compounding","display_name":"Compounding","score":0.8137000203132629},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5916000008583069},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5831999778747559},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.453900009393692},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.43849998712539673},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.420199990272522},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C207673951","wikidata":"https://www.wikidata.org/wiki/Q1303150","display_name":"Compounding","level":2,"score":0.8137000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6527000069618225},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Compounding":[0],"error,":[1],"where":[2],"small":[3],"prediction":[4,65,114],"mistakes":[5],"accumulate":[6],"over":[7],"time,":[8],"presents":[9],"a":[10,51,72,81,161,165,179],"major":[11],"challenge":[12],"in":[13,87,178],"learning-based":[14],"control.":[15],"For":[16],"example,":[17],"this":[18,77,85],"issue":[19],"often":[20],"limits":[21],"the":[22,61,67,88,98,106,117,121],"performance":[23,171],"of":[24,50,63,70,84,90,172],"model-based":[25],"reinforcement":[26],"learning":[27,71],"and":[28,103,137,168,175],"imitation":[29],"learning.":[30],"One":[31],"common":[32],"approach":[33],"to":[34,39,127],"mitigate":[35],"compounding":[36],"error":[37],"is":[38,56,101,124],"train":[40],"multi-step":[41,64,131,166,176],"predictors":[42,132,177],"directly,":[43],"rather":[44],"than":[45],"relying":[46],"on":[47],"autoregressive":[48],"rollout":[49],"single-step":[52,109,140,162],"model.":[53,75],"However,":[54],"it":[55],"not":[57],"well":[58],"understood":[59],"when":[60,97,120],"benefits":[62],"outweigh":[66],"added":[68],"complexity":[69],"more":[73],"complicated":[74],"In":[76],"work,":[78],"we":[79,151],"provide":[80],"rigorous":[82],"analysis":[83],"trade-off":[86],"context":[89],"linear":[91],"dynamical":[92],"systems.":[93],"We":[94],"show":[95],"that":[96],"model":[99,122,163],"class":[100,123],"well-specified":[102],"accurately":[104],"captures":[105],"system":[107],"dynamics,":[108],"models":[110],"achieve":[111],"lower":[112],"asymptotic":[113],"error.":[115],"On":[116],"other":[118],"hand,":[119],"misspecified":[125],"due":[126],"partial":[128],"observability,":[129],"direct":[130],"can":[133],"significantly":[134],"reduce":[135],"bias":[136],"thus":[138],"outperform":[139],"approaches.":[141],"These":[142],"theoretical":[143],"results":[144],"are":[145],"supported":[146],"by":[147],"numerical":[148],"experiments,":[149],"wherein":[150],"also":[152],"(a)":[153],"empirically":[154],"evaluate":[155,170],"an":[156],"intermediate":[157],"strategy":[158],"which":[159],"trains":[160],"using":[164],"loss":[167],"(b)":[169],"single":[173],"step":[174],"closed":[180],"loop":[181],"control":[182],"setting.":[183]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}