{"id":"https://openalex.org/W4387047329","doi":"https://doi.org/10.1137/22m1492088","title":"Approximate Newton Policy Gradient Algorithms","display_name":"Approximate Newton Policy Gradient Algorithms","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387047329","doi":"https://doi.org/10.1137/22m1492088"},"language":"en","primary_location":{"id":"doi:10.1137/22m1492088","is_oa":false,"landing_page_url":"https://doi.org/10.1137/22m1492088","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-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/A5069020700","display_name":"Haoya Li","orcid":"https://orcid.org/0000-0001-7076-7600"},"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":true,"raw_author_name":"Haoya Li","raw_affiliation_strings":["Department of Mathematics, Stanford University, Stanford, CA 94305 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024906908","display_name":"Samarth Gupta","orcid":"https://orcid.org/0000-0001-6225-0230"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samarth Gupta","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsiangfu Yu","raw_affiliation_strings":["Amazon Search, Palo Alto, CA 94303 USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, CA 94303 USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011918131","display_name":"Lexing Ying","orcid":"https://orcid.org/0000-0003-1547-1457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lexing Ying","raw_affiliation_strings":["Department of Mathematics, Stanford University, Stanford, CA 94305-2125 USA, and Amazon Search, Palo Alto, CA 94303 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Stanford University, Stanford, CA 94305-2125 USA, and Amazon Search, Palo Alto, CA 94303 USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inderjit Dhillon","raw_affiliation_strings":["Department of Computer Sciences, University of Texas at Austin, Austin, TX 78712-1188 USA, and Google"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas at Austin, Austin, TX 78712-1188 USA, and Google","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069020700"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.2356,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76138996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"45","issue":"5","first_page":"A2585","last_page":"A2609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9965000152587891,"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":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6301738619804382},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6012778282165527},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.576193630695343},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5336326956748962},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5231184363365173},{"id":"https://openalex.org/keywords/balanced-flow","display_name":"Balanced flow","score":0.5223720669746399},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.476310133934021},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45993566513061523},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.4557459354400635},{"id":"https://openalex.org/keywords/newtons-method-in-optimization","display_name":"Newton's method in optimization","score":0.44135648012161255},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43972548842430115},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41499191522598267},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3719899654388428},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.33314526081085205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3282560110092163},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.2726444602012634},{"id":"https://openalex.org/keywords/local-convergence","display_name":"Local convergence","score":0.18301209807395935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11930426955223083},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.09107491374015808},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08648878335952759}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6301738619804382},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6012778282165527},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.576193630695343},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5336326956748962},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5231184363365173},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.5223720669746399},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.476310133934021},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45993566513061523},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.4557459354400635},{"id":"https://openalex.org/C179127668","wikidata":"https://www.wikidata.org/wiki/Q17086396","display_name":"Newton's method in optimization","level":4,"score":0.44135648012161255},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43972548842430115},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41499191522598267},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3719899654388428},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33314526081085205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3282560110092163},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2726444602012634},{"id":"https://openalex.org/C117898588","wikidata":"https://www.wikidata.org/wiki/Q6664310","display_name":"Local convergence","level":3,"score":0.18301209807395935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11930426955223083},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.09107491374015808},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08648878335952759},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/22m1492088","is_oa":false,"landing_page_url":"https://doi.org/10.1137/22m1492088","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W152055444","https://openalex.org/W1503425191","https://openalex.org/W1600956954","https://openalex.org/W1971945429","https://openalex.org/W2112820497","https://openalex.org/W2119717200","https://openalex.org/W2155216327","https://openalex.org/W2169713291","https://openalex.org/W2492794003","https://openalex.org/W2999905431","https://openalex.org/W3012798594","https://openalex.org/W3023696268","https://openalex.org/W3085158213","https://openalex.org/W3120256427","https://openalex.org/W3126535000","https://openalex.org/W4250589301","https://openalex.org/W4297814233","https://openalex.org/W4301435544"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W1556532828","https://openalex.org/W1574991376","https://openalex.org/W1991138660","https://openalex.org/W3198564127","https://openalex.org/W2146763310","https://openalex.org/W3119377649","https://openalex.org/W4308702637","https://openalex.org/W2997022832"],"abstract_inverted_index":{".Policy":[0],"gradient":[1,42,60,72,88,124],"algorithms":[2,79],"have":[3],"been":[4],"widely":[5],"applied":[6],"to":[7,26,92,102],"Markov":[8],"decision":[9,129],"processes":[10],"and":[11,29,84,99],"reinforcement":[12],"learning":[13],"problems":[14],"in":[15,69,112],"recent":[16],"years.":[17],"Regularization":[18],"with":[19,44],"various":[20],"entropy":[21,45,64],"functions":[22],"is":[23],"often":[24,115],"used":[25],"encourage":[27],"exploration":[28],"improve":[30],"stability.":[31],"This":[32],"paper":[33],"proposes":[34],"an":[35],"approximate":[36,107],"Newton":[37,108,126],"method":[38,67,109],"for":[39],"the":[40,48,53,57,86,93,105],"policy":[41,59,71],"algorithm":[43,55],"regularization.":[46],"In":[47],"case":[49],"of":[50,117],"Shannon":[51],"entropy,":[52],"resulting":[54],"reproduces":[56],"natural":[58],"algorithm.":[61],"For":[62],"other":[63,121],"functions,":[65],"this":[66],"results":[68],"brand-new":[70],"algorithms.":[73],"We":[74,96],"prove":[75],"that":[76,85,104],"all":[77],"these":[78],"enjoy":[80],"Newton-type":[81],"quadratic":[82],"convergence":[83],"corresponding":[87],"flow":[89],"converges":[90,111],"globally":[91],"optimal":[94],"solution.":[95],"use":[97],"synthetic":[98],"industrial-scale":[100],"examples":[101],"demonstrate":[103],"proposed":[106],"typically":[110],"single-digit":[113],"iterations,":[114],"orders":[116],"magnitude":[118],"faster":[119],"than":[120],"state-of-the-art":[122],"algorithms.Keywordspolicy":[123],"algorithmapproximate":[125],"methodquadratic":[127],"convergenceMarkov":[128],"processentropy":[130],"regularizationreinforcement":[131],"learningMSC":[132],"codes49M1565K1068T0590C0690C40":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}