{"id":"https://openalex.org/W7216418045","doi":"https://doi.org/10.48550/arxiv.2610.01546","title":"Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming","display_name":"Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216418045","doi":"https://doi.org/10.48550/arxiv.2610.01546"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01546","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01546","pdf_url":"https://arxiv.org/pdf/2610.01546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114418482","display_name":"Jinhwan Sul","orcid":"https://orcid.org/0000-0001-6283-3575","observed_orcids":["https://orcid.org/0000-0001-6283-3575"]},"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":"Sul, Jinhwan","raw_affiliation_strings":["Georgia Institute of Technology , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055836371","display_name":"Alex Oshin","orcid":"https://orcid.org/0000-0003-4427-0603","observed_orcids":["https://orcid.org/0000-0003-4427-0603"]},"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":"Oshin, Alex","raw_affiliation_strings":["Georgia Institute of Technology , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738","observed_orcids":["https://orcid.org/0000-0002-0834-5738"]},"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":"Theodorou, Evangelos A.","raw_affiliation_strings":["Georgia Institute of Technology , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.42649999260902405,"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":0.42649999260902405,"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":0.3361999988555908,"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/T10545","display_name":"Optimization and Variational Analysis","score":0.03420000150799751,"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/primal-dual-hybrid-gradient","display_name":"primal-dual hybrid gradient","score":0.9829999804496765},{"id":"https://openalex.org/keywords/linear-programming","display_name":"linear programming","score":0.9729999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7459999918937683},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.7670000195503235},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.3959999978542328},{"id":"https://openalex.org/keywords/extrapolation","display_name":"extrapolation","score":0.4909999966621399},{"id":"https://openalex.org/keywords/gallop","display_name":"gallop","score":0.6669999957084656},{"id":"https://openalex.org/keywords/large-scale-optimization","display_name":"large-scale optimization","score":0.6880000233650208},{"id":"https://openalex.org/keywords/transportation-challenges","display_name":"transport problems","score":0.421999990940094},{"id":"https://openalex.org/keywords/item-placement","display_name":"item placement","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7986999750137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413000226020813},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.3325999975204468},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01546","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01546","pdf_url":"https://arxiv.org/pdf/2610.01546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.01546","doi":"https://doi.org/10.48550/arxiv.2610.01546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01546","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01546","pdf_url":"https://arxiv.org/pdf/2610.01546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216418045.pdf","grobid_xml":"https://content.openalex.org/works/W7216418045.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2897417898","https://openalex.org/W2944306386","https://openalex.org/W2965757358","https://openalex.org/W2995038946","https://openalex.org/W2997756832","https://openalex.org/W3034273569","https://openalex.org/W3165200223","https://openalex.org/W3184867364","https://openalex.org/W4224238559","https://openalex.org/W4382243918","https://openalex.org/W4388865538","https://openalex.org/W4390215308","https://openalex.org/W4393147940","https://openalex.org/W4405432974","https://openalex.org/W4409641015","https://openalex.org/W4414700916","https://openalex.org/W4416243214","https://openalex.org/W4416706207","https://openalex.org/W4416966044","https://openalex.org/W6948128564","https://openalex.org/W7123898925","https://openalex.org/W7161265104","https://openalex.org/W7164832160"],"related_works":["https://openalex.org/W6948128564","https://openalex.org/W7164069666","https://openalex.org/W4416243214","https://openalex.org/W7221777268","https://openalex.org/W4414700916","https://openalex.org/W3168933125","https://openalex.org/W7006681885","https://openalex.org/W4416706207","https://openalex.org/W4414846396","https://openalex.org/W7223217156"],"abstract_inverted_index":{"Primal-dual":[0],"hybrid":[1],"gradient":[2],"(PDHG)":[3],"methods":[4],"solve":[5],"large-scale":[6],"linear":[7],"programs":[8],"(LPs)":[9],"using":[10,76],"GPU-friendly":[11],"matrix-vector":[12],"products":[13],"and":[14,26,41,58,63,92,107,129],"projections,":[15],"but":[16],"their":[17],"practical":[18],"performance":[19],"depends":[20],"on":[21,97,103],"coordinating":[22],"algorithm":[23,39,137],"parameters,":[24],"acceleration,":[25],"restarts.":[27],"We":[28,70,100],"introduce":[29],"GALLOP,":[30],"which":[31],"uses":[32],"reinforcement":[33],"learning":[34],"to":[35,132,154],"jointly":[36],"learn":[37],"continuous":[38],"parameters":[40],"discrete":[42],"restart":[43,64,98],"decisions":[44],"without":[45,152],"differentiating":[46],"through":[47],"the":[48,113,118,148,160],"solver.":[49],"Its":[50],"generalized":[51],"accelerated":[52],"PDHG":[53],"update":[54],"combines":[55],"separate":[56],"primal":[57],"dual":[59],"extrapolation,":[60],"history":[61],"corrections,":[62],"anchoring":[65],"with":[66,167],"independently":[67],"adjustable":[68],"coefficients.":[69],"train":[71],"a":[72,77,108,133],"dimension-agnostic":[73],"feedback":[74],"policy":[75,80,144],"groupwise":[78],"proximal":[79],"optimization":[81],"objective":[82],"that":[83],"clips":[84],"likelihood":[85],"ratios":[86],"separately":[87],"for":[88],"different":[89],"control":[90],"groups":[91],"excludes":[93],"inactive":[94],"acceleration":[95],"controls":[96],"transitions.":[99],"evaluate":[101],"GALLOP":[102,121],"six":[104,119],"LP":[105],"families":[106],"public":[109],"item-placement":[110],"benchmark.":[111],"On":[112],"main":[114],"evaluation":[115],"settings":[116],"across":[117],"families,":[120],"reduces":[122],"iteration":[123],"counts":[124],"by":[125],"factors":[126],"of":[127],"$1.9$-$5.6$":[128],"achieves":[130],"up":[131],"$16.0\\times$":[134],"speedup":[135],"in":[136],"wall-clock":[138],"time":[139],"over":[140],"MPAX.":[141],"With":[142],"one":[143],"trained":[145],"per":[146],"family,":[147],"learned":[149],"policies":[150],"generalize":[151],"retraining":[153],"within-family":[155],"LPs":[156,166],"$3\\times$-$400\\times$":[157],"larger":[158],"than":[159],"largest":[161],"training":[162],"instances,":[163],"including":[164],"Transport":[165],"$10.24$":[168],"million":[169],"variables.":[170]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}