{"id":"https://openalex.org/W7123347522","doi":"https://doi.org/10.1109/cdc57313.2025.11312355","title":"Learning Stabilizing Policies via an Unstable Subspace Representation","display_name":"Learning Stabilizing Policies via an Unstable Subspace Representation","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123347522","doi":"https://doi.org/10.1109/cdc57313.2025.11312355"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312355","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":"conference-paper","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/A5048610577","display_name":"Leonardo Toso","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo F. Toso","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102978887","display_name":"Lintao Ye","orcid":"https://orcid.org/0000-0003-0337-1651"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lintao Ye","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Artificial Intelligence and Automation,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":null,"display_name":"James Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Anderson","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93114241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7543","last_page":"7550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5418000221252441,"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"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5418000221252441,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.11420000344514847,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.10819999873638153,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/subspace-topology","display_name":"Subspace topology","score":0.8269000053405762},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.617900013923645},{"id":"https://openalex.org/keywords/quadratic-growth","display_name":"Quadratic growth","score":0.6054999828338623},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5587999820709229},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.421099990606308}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.8269000053405762},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.617900013923645},{"id":"https://openalex.org/C195956108","wikidata":"https://www.wikidata.org/wiki/Q7268362","display_name":"Quadratic growth","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.534600019454956},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34619998931884766},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312355","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4074828326702118}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W203276351","https://openalex.org/W1970377488","https://openalex.org/W2046402929","https://openalex.org/W2046550033","https://openalex.org/W3031802121","https://openalex.org/W3046992251","https://openalex.org/W3098412154","https://openalex.org/W3119327948","https://openalex.org/W3166923021","https://openalex.org/W4250954493","https://openalex.org/W4312258136","https://openalex.org/W4367841446","https://openalex.org/W4391021934","https://openalex.org/W4402300769","https://openalex.org/W4403929531","https://openalex.org/W4407949646","https://openalex.org/W7123340430","https://openalex.org/W7123347522"],"related_works":[],"abstract_inverted_index":{"We":[0,70,116],"study":[1],"the":[2,35,49,55,67,78,83,98,105,110,114,128,137,146,151],"problem":[3,57],"of":[4,34,61,82,90,113,139],"learning":[5,48],"to":[6,19],"stabilize":[7],"(LTS)":[8],"a":[9,26,59,72,88],"linear":[10,92],"system.":[11],"Policy":[12],"gradient":[13],"methods":[14],"for":[15,28,120],"control":[16],"assume":[17],"access":[18],"an":[20,29],"initial":[21],"stabilizing":[22],"policy.":[23,51],"Designing":[24],"such":[25],"policy":[27],"unknown":[30],"system":[31,84],"is":[32,142],"one":[33],"most":[36],"fundamental":[37],"problems":[38,96],"in":[39],"control,":[40],"and":[41,85,123],"it":[42],"may":[43],"be":[44],"as":[45,47],"hard":[46],"optimal":[50],"Existing":[52],"work":[53],"on":[54,97,127,150],"LTS":[56,149],"requires":[58],"volume":[60],"data":[62],"that":[63,75,125],"scales":[64],"quadratically":[65],"with":[66],"ambient":[68],"dimension.":[69],"propose":[71],"two-phase":[73],"approach":[74],"first":[76],"learns":[77],"left":[79],"unstable":[80,100,106,129,140,152],"subspace":[81,130,153],"then":[86],"solves":[87],"series":[89],"discounted":[91],"quadratic":[93],"regulator":[94],"(LQR)":[95],"learned":[99],"subspace.":[101],"By":[102],"targeting":[103],"just":[104],"dynamics,":[107],"we":[108],"reduce":[109],"effective":[111],"dimension":[112],"problem.":[115],"provide":[117],"non-asymptotic":[118],"guarantees":[119],"both":[121],"phases":[122],"demonstrate":[124],"operating":[126],"reduces":[131],"sample":[132],"complexity.":[133],"In":[134],"particular,":[135],"when":[136],"number":[138],"modes":[141],"much":[143],"smaller":[144],"than":[145],"state":[147],"dimension,":[148],"substantially":[154],"speeds":[155],"up":[156],"stabilization.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-14T00:00:00"}