{"id":"https://openalex.org/W7160848588","doi":"https://doi.org/10.48550/arxiv.2605.07661","title":"Stochastic Transition-Map Distillation for Fast Probabilistic Inference","display_name":"Stochastic Transition-Map Distillation for Fast Probabilistic Inference","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160848588","doi":"https://doi.org/10.48550/arxiv.2605.07661"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07661","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079918659","display_name":"George Rapakoulias","orcid":"https://orcid.org/0009-0000-8572-710X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rapakoulias, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135860303","display_name":"Peter Garud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garud, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135876401","display_name":"Lingjiong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Lingjiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077667229","display_name":"Panagiotis Tsiotras","orcid":"https://orcid.org/0000-0001-7563-4129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsiotras, Panagiotis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8093000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8093000054359436,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.04399999976158142,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"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":0.03660000115633011,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6018000245094299},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.5910000205039978},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.551800012588501},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.44040000438690186},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4318000078201294},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41839998960494995},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4171999990940094},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4108999967575073}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.5910000205039978},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5289999842643738},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42250001430511475},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.3116999864578247},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07661","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07661","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,49],"achieve":[2],"strong":[3,155],"generation":[4,167],"quality,":[5],"diversity,":[6],"and":[7,117,135,139,161,173],"distribution":[8],"coverage,":[9],"but":[10],"their":[11],"performance":[12],"often":[13],"comes":[14],"with":[15,63,75],"expensive":[16],"inference.":[17],"In":[18,40],"this":[19],"work,":[20],"we":[21],"propose":[22],"Stochastic":[23],"Transition-Map":[24],"Distillation":[25],"(STMD),":[26],"a":[27,76,82,154],"teacher-free":[28],"framework":[29],"for":[30,103,146,158],"accelerating":[31],"diffusion":[32,44,96,112],"model":[33],"inference":[34],"while":[35],"preserving":[36],"probabilistic":[37],"sample":[38],"generation.":[39],"contrast":[41],"to":[42,121],"score-based":[43],"models,":[45],"whose":[46],"denoising":[47],"parametrization":[48],"the":[50,53,58,64,90,94,150,170],"mean":[51],"of":[52,93],"posterior":[54,113],"distribution,":[55],"STMD":[56,125,163],"distills":[57],"full":[59],"transition":[60,91],"map":[61],"associated":[62],"sampling":[65],"stochastic":[66,86,108],"differential":[67],"equation":[68],"(SDE).":[69],"We":[70,142],"parameterize":[71],"these":[72],"SDE":[73],"transitions":[74],"conditional":[77],"Mean":[78],"Flow":[79],"model,":[80],"yielding":[81],"one-":[83],"or":[84,132],"few-step":[85],"sampler":[87],"that":[88,106],"retains":[89],"structure":[92],"underlying":[95],"process.":[97],"This":[98],"perspective":[99],"is":[100],"especially":[101],"useful":[102],"downstream":[104],"tasks":[105],"require":[107],"inference,":[109],"such":[110],"as":[111],"sampling,":[114],"inverse":[115],"problems,":[116],"energy-based":[118],"fine-tuning.":[119],"Compared":[120],"recent":[122],"distillation":[123],"methods,":[124],"requires":[126],"no":[127],"pretrained":[128],"teacher,":[129],"bi-level":[130],"optimization,":[131],"trajectory":[133],"simulation":[134],"caching,":[136],"enabling":[137],"efficient":[138],"scalable":[140],"training.":[141],"derive":[143],"convergence":[144],"bounds":[145],"our":[147,159],"method":[148],"in":[149],"Wasserstein":[151],"distance,":[152],"providing":[153],"theoretical":[156],"foundation":[157],"approach,":[160],"validate":[162],"on":[164,169],"various":[165],"image":[166],"examples":[168],"MNIST,":[171],"CIFAR-10,":[172],"CelebA":[174],"datasets.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-12T00:00:00"}