{"id":"https://openalex.org/W7204855785","doi":"https://doi.org/10.48550/arxiv.2608.27884","title":"Exploiting Exact Conditionals Improves Conditioning: Provably Fast Mixing Time Bounds By Sampling from the Marginal","display_name":"Exploiting Exact Conditionals Improves Conditioning: Provably Fast Mixing Time Bounds By Sampling from the Marginal","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204855785","doi":"https://doi.org/10.48550/arxiv.2608.27884"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27884","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27884","pdf_url":"https://arxiv.org/pdf/2608.27884","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.27884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082468966","display_name":"Abhijit Chowdhary","orcid":"https://orcid.org/0000-0002-5092-3503","observed_orcids":["https://orcid.org/0000-0002-5092-3503"]},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chowdhary, Abhijit","raw_affiliation_strings":["Department of Mathematics , Tufts University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , Tufts University","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083030731","display_name":"Federica Milinanni","orcid":"https://orcid.org/0000-0003-3635-8760","observed_orcids":["https://orcid.org/0000-0003-3635-8760"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH","US"],"is_corresponding":false,"raw_author_name":"Milinanni, Federica","raw_affiliation_strings":["Department of Industrial Engineering and Management Sciences , Northwestern University (feder-"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Sciences , Northwestern University (feder-","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136104636","display_name":"Julianne Chung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung, Julianne","raw_affiliation_strings":["Department of Mathematics , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090161771","display_name":"Elizabeth Newman","orcid":"https://orcid.org/0000-0002-6309-7706","observed_orcids":["https://orcid.org/0000-0002-6309-7706"]},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Newman, Elizabeth","raw_affiliation_strings":["Department of Mathematics , Tufts University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , Tufts University","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":1.0,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0,"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/T10591","display_name":"Theoretical and Computational Physics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter 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/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.8360000252723694},{"id":"https://openalex.org/keywords/metropolis-hastings-algorithm","display_name":"Metropolis-Hastings algorithm","score":0.8429999947547913},{"id":"https://openalex.org/keywords/spectral-gap","display_name":"spectral gap","score":0.8650000095367432},{"id":"https://openalex.org/keywords/asymptotic-variance","display_name":"asymptotic variance","score":0.9869999885559082},{"id":"https://openalex.org/keywords/posterior-sampling","display_name":"posterior sampling","score":0.7310000061988831},{"id":"https://openalex.org/keywords/image-deblurring","display_name":"image deblurring","score":0.6919999718666077}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.7360000014305115},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.6739000082015991},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5965999960899353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5741999745368958},{"id":"https://openalex.org/C187192777","wikidata":"https://www.wikidata.org/wiki/Q381699","display_name":"Rejection sampling","level":5,"score":0.5666999816894531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.542900025844574},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5180000066757202},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C165216359","wikidata":"https://www.wikidata.org/wiki/Q670653","display_name":"Marginal distribution","level":3,"score":0.47530001401901245},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.46619999408721924},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.4271000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39809998869895935},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C204693719","wikidata":"https://www.wikidata.org/wiki/Q910810","display_name":"Metropolis\u2013Hastings algorithm","level":4,"score":0.3598000109195709},{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.3564000129699707},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C95923904","wikidata":"https://www.wikidata.org/wiki/Q6760420","display_name":"Marginal likelihood","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.26030001044273376},{"id":"https://openalex.org/C97074811","wikidata":"https://www.wikidata.org/wiki/Q6771322","display_name":"Markov chain mixing time","level":5,"score":0.26010000705718994},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27884","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27884","pdf_url":"https://arxiv.org/pdf/2608.27884","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27884","doi":"https://doi.org/10.48550/arxiv.2608.27884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27884","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27884","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27884","pdf_url":"https://arxiv.org/pdf/2608.27884","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1287316037","display_name":"Institute for Computational and Experimental Research in Mathematics","funder_award_id":"1929284","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5592393793","display_name":"Collaborative Research: Randomized algorithms for dynamic and hierarchical Bayesian inverse problems","funder_award_id":"2411197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5934365228","display_name":"Learnable Tensor Algebras for Harnessing Implicit Correlations in Multiway Data","funder_award_id":"2309751","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204855785.pdf","grobid_xml":"https://content.openalex.org/works/W7204855785.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W32980360","https://openalex.org/W81502470","https://openalex.org/W143236119","https://openalex.org/W1788547584","https://openalex.org/W1809030594","https://openalex.org/W1995713768","https://openalex.org/W2020999234","https://openalex.org/W2033765726","https://openalex.org/W2045656233","https://openalex.org/W2050568249","https://openalex.org/W2056760934","https://openalex.org/W2058699951","https://openalex.org/W2065284301","https://openalex.org/W2107614102","https://openalex.org/W2135194391","https://openalex.org/W2136796925","https://openalex.org/W2138309709","https://openalex.org/W2222154095","https://openalex.org/W2389866904","https://openalex.org/W2577537660","https://openalex.org/W2899349102","https://openalex.org/W2905060647","https://openalex.org/W2920804790","https://openalex.org/W2995576031","https://openalex.org/W3044941140","https://openalex.org/W3202046707","https://openalex.org/W4245232001","https://openalex.org/W4246327874","https://openalex.org/W4254476808","https://openalex.org/W4292691288","https://openalex.org/W4393002334","https://openalex.org/W4401057266","https://openalex.org/W4401403169","https://openalex.org/W4402383094","https://openalex.org/W4404144650","https://openalex.org/W4406168614","https://openalex.org/W4412112838","https://openalex.org/W4415798426","https://openalex.org/W7140901348"],"related_works":["https://openalex.org/W7133251602","https://openalex.org/W4388319634","https://openalex.org/W1675872272","https://openalex.org/W3099089001","https://openalex.org/W2106781191","https://openalex.org/W2137004152","https://openalex.org/W3036554994","https://openalex.org/W2167943787","https://openalex.org/W2268031802","https://openalex.org/W130585985"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,123,168,197],"sampling":[3,15,37,94,101,149],"from":[4,38,95,102,150],"a":[5,39,62,68,85,89,111,176,206],"probability":[6,41],"distribution":[7,58,66,70],"arises":[8],"in":[9,16],"many":[10],"applications":[11],"such":[12,84],"as":[13],"posterior":[14],"hierarchical":[17],"Bayesian":[18],"inverse":[19],"problems":[20],"and":[21,67,87,132,181,199],"Gaussian":[22],"processes":[23],"for":[24,36,50,202],"machine":[25],"learning.":[26],"Markov":[27,90,112],"chain":[28,91,113],"Monte":[29],"Carlo":[30],"(MCMC)":[31],"algorithms":[32],"are":[33,200],"often":[34],"used":[35],"target":[40,57],"distribution,":[42,98],"but":[43],"implementations":[44],"can":[45,139],"be":[46],"computationally":[47],"expensive,":[48],"especially":[49],"large-scale":[51],"problems.":[52],"In":[53],"certain":[54],"applications,":[55],"the":[56,96,103,115,120,124,151,166,194],"naturally":[59],"factorizes":[60],"into":[61],"lower":[63],"dimensional":[64],"marginal":[65,97,125],"conditional":[69,105],"that":[71,82,118,137,159,173],"allows":[72],"exact":[73,104],"sampling.":[74],"We":[75,135],"describe":[76],"an":[77],"MCMC":[78,126],"algorithm":[79],"called":[80],"MarCo":[81,109,138,174,198],"exploits":[83],"structure":[86],"generates":[88],"via":[92],"Metropolis-Hastings":[93],"followed":[99],"by":[100],"distribution.":[106,153],"By":[107],"design,":[108],"constructs":[110],"on":[114],"joint":[116,152],"space":[117],"inherits":[119],"convergence":[121,189],"behavior":[122],"algorithm.":[127],"This":[128],"provides":[129],"multiple":[130],"theoretical":[131],"computational":[133],"advantages.":[134],"prove":[136],"achieve":[140],"improved":[141],"mixing":[142],"time":[143],"upper":[144],"bounds":[145],"compared":[146,155],"to":[147,156,171,187],"direct":[148],"Moreover,":[154],"one-block":[157],"methods":[158],"also":[160],"exploit":[161],"marginal-conditional":[162],"structure,":[163],"we":[164],"use":[165],"framework":[167],"Peskun-Tierney":[169],"ordering":[170],"show":[172],"has":[175],"larger":[177],"right":[178],"spectral":[179],"gap":[180],"smaller":[182],"asymptotic":[183],"variance,":[184],"thus":[185],"leading":[186],"superior":[188],"properties.":[190],"Numerical":[191],"results":[192],"illustrate":[193],"performance":[195],"benefits":[196],"provided":[201],"various":[203],"problems,":[204],"including":[205],"semi-blind":[207],"image":[208],"deblurring":[209],"example.":[210]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}