{"id":"https://openalex.org/W7154710297","doi":"https://doi.org/10.48550/arxiv.2604.15114","title":"Amortized Optimal Transport from Sliced Potentials","display_name":"Amortized Optimal Transport from Sliced Potentials","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154710297","doi":"https://doi.org/10.48550/arxiv.2604.15114"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15114","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133718120","display_name":"Minh-Phuc Truong","orcid":"https://orcid.org/0009-0005-3834-4882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Truong, Minh-Phuc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068254112","display_name":"Khai Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Khai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.1137000024318695,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.1137000024318695,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.10670000314712524,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.06949999928474426,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/amortization","display_name":"Amortization","score":0.7681999802589417},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6320000290870667},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5055000185966492},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4027999937534332},{"id":"https://openalex.org/keywords/amortized-analysis","display_name":"Amortized analysis","score":0.40149998664855957},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C2781198434","wikidata":"https://www.wikidata.org/wiki/Q4064479","display_name":"Amortization","level":3,"score":0.7681999802589417},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6176999807357788},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5055000185966492},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C142417499","wikidata":"https://www.wikidata.org/wiki/Q331716","display_name":"Amortized analysis","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35269999504089355},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15114","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.15114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15114","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,"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"},"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":{"We":[0,26,169],"propose":[1],"a":[2,42],"novel":[3],"amortized":[4,103],"optimization":[5],"method":[6],"for":[7],"predicting":[8],"optimal":[9],"transport":[10],"(OT)":[11],"plans":[12],"across":[13,117],"multiple":[14],"pairs":[15,120],"of":[16,78,149,152,159,173],"measures":[17],"by":[18,82,121,134,139],"leveraging":[19],"Kantorovich":[20,48,85],"potentials":[21,49],"derived":[22],"from":[23,50,60,98,125],"sliced":[24,61,140],"OT.":[25],"introduce":[27],"two":[28],"amortization":[29,32,36],"strategies:":[30],"regression-based":[31],"(RA-OT)":[33],"and":[34,57,65,108,189],"objective-based":[35],"(OA-OT).":[37],"In":[38,72,88],"RA-OT,":[39],"we":[40,74],"formulate":[41],"functional":[43,80],"regression":[44],"model":[45,81],"that":[46],"treats":[47],"the":[51,76,79,84,91,99,136,142,153,157,162,171],"original":[52],"OT":[53,62,93,104,115,191],"problem":[54],"as":[55,63,156],"responses":[56],"those":[58],"obtained":[59],"predictors,":[64],"estimate":[66,75],"these":[67],"models":[68,144],"via":[69],"least-squares":[70],"methods.":[71],"OA-OT,":[73],"parameters":[77],"optimizing":[83],"dual":[86],"objective.":[87],"both":[89,106],"approaches,":[90],"predicted":[92],"plan":[94],"is":[95],"subsequently":[96],"recovered":[97],"estimated":[100],"potentials.":[101],"As":[102],"methods,":[105],"RA-OT":[107],"OA-OT":[109],"enable":[110],"efficient":[111],"solutions":[112],"to":[113,128],"repeated":[114],"problems":[116],"different":[118],"measure":[119],"reusing":[122],"information":[123],"learned":[124],"prior":[126],"instances":[127],"rapidly":[129],"approximate":[130],"new":[131],"solutions.":[132],"Moreover,":[133],"exploiting":[135],"structure":[137],"provided":[138],"OT,":[141],"proposed":[143],"are":[145],"more":[146],"parsimonious,":[147],"independent":[148],"specific":[150],"structures":[151],"measures,":[154],"such":[155],"number":[158],"atoms":[160],"in":[161],"discrete":[163],"case,":[164],"while":[165],"achieving":[166],"high":[167],"accuracy.":[168],"demonstrate":[170],"effectiveness":[172],"our":[174],"approaches":[175],"on":[176,186],"tasks":[177],"including":[178],"MNIST":[179],"digit":[180],"transport,":[181],"color":[182],"transfer,":[183],"supply-demand":[184],"transportation":[185],"spherical":[187],"data,":[188],"mini-batch":[190],"conditional":[192],"flow":[193],"matching.":[194]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-18T00:00:00"}