{"id":"https://openalex.org/W7123351784","doi":"https://doi.org/10.1109/cdc57313.2025.11312393","title":"Finite-Time Bounds for Two-Time-Scale Stochastic Approximation with Arbitrary Norm Contractions and Markovian Noise","display_name":"Finite-Time Bounds for Two-Time-Scale Stochastic Approximation with Arbitrary Norm Contractions and Markovian Noise","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123351784","doi":"https://doi.org/10.1109/cdc57313.2025.11312393"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312393","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/A5057820085","display_name":"Siddharth Chandak","orcid":"https://orcid.org/0000-0003-3237-7729"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Chandak","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085090559","display_name":"Shaan Ul Haque","orcid":"https://orcid.org/0000-0001-9557-4071"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaan Ul Haque","raw_affiliation_strings":["Georgia Institute of Technology,Industrial and Systems Engineering,Atlanta,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Industrial and Systems Engineering,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002056995","display_name":"Nicholas Bambos","orcid":"https://orcid.org/0000-0001-9250-4553"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Bambos","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91374125,"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":"6095","last_page":"6101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7664999961853027,"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":0.7664999961853027,"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/T11031","display_name":"Game Theory and Applications","score":0.09220000356435776,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.025100000202655792,"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/monotone-polygon","display_name":"Monotone polygon","score":0.605400025844574},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.49320000410079956},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48510000109672546},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4765999913215637},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.3544999957084656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3506999909877777},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.34860000014305115},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.3443000018596649},{"id":"https://openalex.org/keywords/fixed-point","display_name":"Fixed point","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.49320000410079956},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4765999913215637},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35420000553131104},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2988709989","wikidata":"https://www.wikidata.org/wiki/Q85784623","display_name":"Mean square","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C135692309","wikidata":"https://www.wikidata.org/wiki/Q111124","display_name":"Square (algebra)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C193386753","wikidata":"https://www.wikidata.org/wiki/Q1130396","display_name":"Approximations of \u03c0","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C12715386","wikidata":"https://www.wikidata.org/wiki/Q7624691","display_name":"Strongly monotone","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312393","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":19,"referenced_works":["https://openalex.org/W594357522","https://openalex.org/W1491706803","https://openalex.org/W1557517019","https://openalex.org/W1977794212","https://openalex.org/W1985291828","https://openalex.org/W2075268401","https://openalex.org/W2086161653","https://openalex.org/W2103406407","https://openalex.org/W2147750403","https://openalex.org/W2154204727","https://openalex.org/W2963319047","https://openalex.org/W2996964934","https://openalex.org/W3097149416","https://openalex.org/W3173526354","https://openalex.org/W4302033506","https://openalex.org/W4387401525","https://openalex.org/W4392587904","https://openalex.org/W4409748086","https://openalex.org/W7123351784"],"related_works":[],"abstract_inverted_index":{"Two-time-scale":[0],"Stochastic":[1],"Approximation":[2],"(SA)":[3],"is":[4,90],"an":[5,129,161],"iterative":[6],"algorithm":[7,130,162],"with":[8,27,51,112,150],"applications":[9,36],"in":[10,37,72,82],"reinforcement":[11,38],"learning":[12,164],"and":[13,56,76,105,159],"optimization.":[14],"Prior":[15],"finite-time":[16],"analyses":[17],"of":[18,70,80,107,134,146,156,178],"such":[19],"algorithms":[20],"have":[21],"focused":[22],"on":[23],"fixed":[24],"point":[25],"iterations":[26],"mappings":[28,55],"contractive":[29,54],"under":[30,136],"the":[31,42,62,73,87,95,101,113,118,124,137],"Euclidean":[32],"norm.":[33],"Motivated":[34],"by":[35],"learning,":[39],"we":[40,122],"give":[41,123],"first":[43,125],"mean":[44,63],"square":[45,64],"bound":[46,127],"for":[47,128,131,148,163,169],"non-linear":[48],"two-time-scale":[49],"SA":[50],"arbitrary":[52,102],"norm":[53,103],"Markovian":[57,114],"noise.":[58,115],"We":[59,141],"show":[60],"that":[61],"error":[65],"decays":[66],"at":[67,77,175],"a":[68,78,83,144,153,176],"rate":[69,79,145,177],"${\\mathcal{O}}\\left({1/{n^{2/3}}}\\right)$":[71],"general":[74],"case,":[75],"${\\mathcal{O}}(1/n)$":[81,126,147],"special":[84,154],"case":[85,155],"where":[86],"slower":[88],"timescale":[89],"noiseless.":[91],"Our":[92],"analysis":[93],"uses":[94],"generalized":[96],"Moreau":[97],"envelope":[98],"to":[99,110],"handle":[100],"contractions":[104],"solutions":[106],"Poisson":[108],"equation":[109],"deal":[111],"By":[116],"analyzing":[117],"SSP":[119],"Q-Learning":[120,149],"algorithm,":[121],"asynchronous":[132],"control":[133],"MDPs":[135],"average":[138],"reward":[139],"criterion.":[140],"also":[142],"obtain":[143],"Polyak-averaging":[151],"as":[152],"our":[157],"result":[158],"provide":[160],"Generalized":[165],"Nash":[166],"Equilibrium":[167],"(GNE)":[168],"strongly":[170],"monotone":[171],"games":[172],"which":[173],"converges":[174],"${\\mathcal{O}}\\left({1/{n^{2/3}}}\\right)$.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}