{"id":"https://openalex.org/W7162336444","doi":"https://doi.org/10.48550/arxiv.2605.23434","title":"Onsager-Machlup Posterior Transport for Deep Gaussian Processes","display_name":"Onsager-Machlup Posterior Transport for Deep Gaussian Processes","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162336444","doi":"https://doi.org/10.48550/arxiv.2605.23434"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.23434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23434","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.23434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136898145","display_name":"Jian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136897850","display_name":"Delu Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Delu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136951741","display_name":"John Paisley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paisley, John","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136948545","display_name":"Qibin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Qibin","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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9010000228881836,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9010000228881836,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.028599999845027924,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010700000450015068,"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/path","display_name":"Path (computing)","score":0.644599974155426},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5216000080108643},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5112000107765198},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5070000290870667},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4521999955177307},{"id":"https://openalex.org/keywords/brownian-bridge","display_name":"Brownian bridge","score":0.44440001249313354},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.40310001373291016}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6880000233650208},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4521999955177307},{"id":"https://openalex.org/C78651780","wikidata":"https://www.wikidata.org/wiki/Q628309","display_name":"Brownian bridge","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.40059998631477356},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25099998712539673},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.23434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23434","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.23434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23434","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.49648815393447876,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Approximate":[0],"inference":[1,39],"over":[2],"inducing":[3,55],"variables":[4],"is":[5,86,100,113],"the":[6,64,83,89,97,101,105,111,114,131,138,147,178,187,236,239],"central":[7],"computational":[8],"bottleneck":[9],"of":[10,119,190,238],"Deep":[11],"Gaussian":[12],"Processes":[13],"(DGPs).":[14],"Existing":[15],"methods":[16],"either":[17],"fit":[18],"an":[19,24],"explicit":[20],"density":[21,118],"$q_\u03d5(\\bU)$":[22],"by":[23,32,58],"ELBO":[25,144],"(DSVI,":[26],"IPVI,":[27],"DDVI,":[28],"DBVI)":[29],"or":[30],"sample":[31],"MCMC":[33],"(SGHMC).":[34],"We":[35],"instead":[36],"frame":[37],"DGP":[38],"as":[40,157],"\\emph{posterior":[41],"transport}:":[42],"learn":[43],"a":[44,49,59,120,160],"deterministic":[45],"sampler":[46],"that":[47],"maps":[48],"tractable":[50],"reference":[51,66,84],"measure":[52],"to":[53,78,215],"posterior-relevant":[54],"variables,":[56],"regularised":[57],"path":[60,98,123,136,240],"prior":[61],"derived":[62,156],"from":[63,88],"Doob-bridged":[65,80],"diffusion.":[67],"Our":[68],"realisation,":[69],"\\textbf{OM-Path}":[70],"(formally":[71],"FBVI-bridge-Path),":[72],"uses":[73],"Song's":[74],"probability-flow":[75],"ODE":[76],"applied":[77],"DBVI's":[79],"forward":[81],"SDE;":[82],"drift":[85],"closed-form":[87],"bridge":[90,149],"marginal":[91],"coefficients":[92],"(no":[93],"score":[94],"matching)":[95],"and":[96,125,208],"regulariser":[99],"\\textbf{Onsager--Machlup":[102],"action}.":[103],"At":[104],"finite-$\u03b5$":[106],"value":[107],"used":[108],"at":[109],"training,":[110],"objective":[112,241],"negative":[115],"log":[116],"unnormalised":[117],"tempered":[121],"Doob-bridge":[122],"posterior,":[124],"Theorem":[126],"1":[127],"identifies":[128],"it":[129],"with":[130],"same":[132,148],"posterior's":[133],"small-noise":[134],"MAP":[135],"via":[137],"Freidlin--Wentzell":[139],"LDP.":[140],"Two":[141],"strict":[142],"path-space":[143],"variants":[145,223],"on":[146,167,177,204,217,228],"backbone":[150],"(FFJORD":[151],"log-det;":[152],"OM-regularised":[153],"CNF)":[154],"are":[155],"ablations.":[158],"Under":[159],"matched-seed":[161],"paired":[162],"Wilcoxon":[163],"test":[164],"against":[165],"DBVI":[166,216,227],"seven":[168],"UCI":[169,230],"regression":[170],"benchmarks,":[171],"OM-Path":[172],"delivers":[173],"statistically":[174],"significant":[175],"wins":[176],"two":[179],"largest":[180],"datasets":[181],"(\\textit{power}:":[182],"$p\\!=\\!0.014$,":[183],"NLL":[184,198],"$\\mathbf{0.012}$":[185],"matching":[186],"DSVI":[188],"baseline":[189],"$0.017$;":[191],"\\textit{protein}:":[192],"$p\\!=\\!0.002$,":[193],"RMSE":[194],"$\\mathbf{0.716}$":[195],"vs.\\":[196,200],"$0.764$,":[197],"$\\mathbf{1.086}$":[199],"$1.149$),":[201],"statistical":[202],"ties":[203],"\\textit{yacht}":[205],"/":[206,211,213],"\\textit{qsar},":[207],"concedes":[209],"\\textit{boston}":[210],"\\textit{energy}":[212],"\\textit{concrete}":[214],"small-$N$":[218],"noisy":[219],"data.":[220],"The":[221],"strict-ELBO":[222],"do":[224],"not":[225],"clear":[226],"any":[229],"metric:":[231],"in":[232],"this":[233],"regime,":[234],"reducing":[235],"variance":[237],"dominates":[242],"exact-density":[243],"tracking.":[244]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-26T00:00:00"}