{"id":"https://openalex.org/W7214079372","doi":"https://doi.org/10.48550/arxiv.2609.25675","title":"Marginal Log-Likelihood Increments under Dirichlet-Smoothed Markov Estimation","display_name":"Marginal Log-Likelihood Increments under Dirichlet-Smoothed Markov Estimation","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214079372","doi":"https://doi.org/10.48550/arxiv.2609.25675"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.25675","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25675","pdf_url":"https://arxiv.org/pdf/2609.25675","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/2609.25675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152543397","display_name":"Levin David Schwab","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Schwab, Levin David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5152543397"],"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9169999957084656,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9169999957084656,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.009800000116229057,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.003700000001117587,"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/markov-chain-estimation","display_name":"Markov chain estimation","score":0.6320000290870667},{"id":"https://openalex.org/keywords/process-mining","display_name":"process mining","score":0.5830000042915344},{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.8970000147819519},{"id":"https://openalex.org/keywords/submodularity","display_name":"submodular functions","score":0.781000018119812},{"id":"https://openalex.org/keywords/supermodularity","display_name":"supermodularity","score":0.9589999914169312},{"id":"https://openalex.org/keywords/batch-optimization","display_name":"batch optimization","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8270999789237976},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C165216359","wikidata":"https://www.wikidata.org/wiki/Q670653","display_name":"Marginal distribution","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C9490382","wikidata":"https://www.wikidata.org/wiki/Q729113","display_name":"Weighted arithmetic mean","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C2776709221","wikidata":"https://www.wikidata.org/wiki/Q6031040","display_name":"Information Criteria","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.25675","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25675","pdf_url":"https://arxiv.org/pdf/2609.25675","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.2609.25675","doi":"https://doi.org/10.48550/arxiv.2609.25675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.25675","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:2609.25675","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25675","pdf_url":"https://arxiv.org/pdf/2609.25675","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/W7214079372.pdf","grobid_xml":"https://content.openalex.org/works/W7214079372.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1680189815","https://openalex.org/W1999120268","https://openalex.org/W2964066696","https://openalex.org/W4323306227","https://openalex.org/W4415798825","https://openalex.org/W6948214015","https://openalex.org/W7204564801"],"related_works":["https://openalex.org/W7099673847","https://openalex.org/W3021551990","https://openalex.org/W3169714948","https://openalex.org/W2494067213","https://openalex.org/W2954228454","https://openalex.org/W2222316976","https://openalex.org/W7099055435","https://openalex.org/W2909379646","https://openalex.org/W2521506871","https://openalex.org/W7095908327"],"abstract_inverted_index":{"For":[0],"a":[1,33,63,67,85,119],"Dirichlet-smoothed":[2],"transition":[3],"model,":[4],"the":[5,13,40,44,55,78,81,89,96,108,126,146,161,165],"effect":[6,79],"of":[7,36,69,80,125,129,136,164],"adding":[8],"one":[9,124,147],"workflow":[10],"trace":[11],"to":[12,58,140],"training":[14],"archive":[15],"is":[16,32,71,99,179],"an":[17,51,73],"exact":[18,74],"change":[19,27],"in":[20,123],"reference-weighted":[21],"log":[22,113],"likelihood.":[23],"We":[24],"derive":[25],"that":[26,30,148],"and":[28,43,84,117,132,143],"show":[29],"it":[31],"weighted":[34],"reduction":[35],"Kullback--Leibler":[37],"divergence":[38],"between":[39,91],"reference":[41,82,130],"conditionals":[42],"model.":[45],"From":[46],"this":[47],"form":[48],"we":[49],"obtain":[50],"upper":[52],"bound":[53],"on":[54,107],"gain":[56],"available":[57],"any":[59],"acquisition,":[60],"which":[61,95],"expresses":[62],"millinat":[64],"difference":[65],"as":[66],"share":[68,163],"what":[70],"attainable,":[72],"covariance":[75],"identity":[76],"for":[77,88,176,184],"weighting,":[83],"sign":[86],"criterion":[87],"interaction":[90],"two":[92,137],"candidates,":[93],"from":[94],"batch":[97,185],"objective":[98],"neither":[100,180],"submodular":[101],"nor":[102,182],"supermodular.":[103],"A":[104],"case":[105],"study":[106],"BPI":[109],"Challenge":[110],"2012":[111],"loan-application":[112],"measures":[114],"all":[115],"three":[116],"finds":[118],"positive":[120],"selection":[121],"result":[122],"four":[127],"combinations":[128],"weighting":[131],"budget":[133],"unit.":[134],"There,":[135],"regressors":[138],"fitted":[139],"identical":[141,144],"descriptors":[142],"labels,":[145],"predicts":[149],"individual":[150,177],"increments":[151],"far":[152],"more":[153],"accurately,":[154],"median":[155],"$R^2$":[156],"0.87":[157],"against":[158,169],"0.62,":[159],"realizes":[160],"smaller":[162],"attainable":[166],"gain,":[167],"61":[168],"69":[170],"per":[171],"cent,":[172],"so":[173],"ranking":[174],"accuracy":[175],"traces":[178],"necessary":[181],"sufficient":[183],"quality.":[186]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}