{"id":"https://openalex.org/W4416936451","doi":"https://doi.org/10.48550/arxiv.2512.00397","title":"An RKHS Perspective on Tree Ensembles","display_name":"An RKHS Perspective on Tree Ensembles","publication_year":2025,"publication_date":"2025-11-29","ids":{"openalex":"https://openalex.org/W4416936451","doi":"https://doi.org/10.48550/arxiv.2512.00397"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2512.00397","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00397","pdf_url":"https://arxiv.org/pdf/2512.00397","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/2512.00397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037802114","display_name":"Mehdi Dagdoug","orcid":"https://orcid.org/0009-0004-9813-9568","observed_orcids":["https://orcid.org/0009-0004-9813-9568"]},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dagdoug, Mehdi","raw_affiliation_strings":["McGill University , Department of Mathematics and Statistics Montr\u00e9al , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University , Department of Mathematics and Statistics Montr\u00e9al , Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017600653","display_name":"Cl\u00e9ment Dombry","orcid":"https://orcid.org/0000-0003-2382-3280","observed_orcids":["https://orcid.org/0000-0003-2382-3280"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4387152972","display_name":"Laboratoire de Math\u00e9matiques de Besan\u00e7on","ror":"https://ror.org/04nrhwg12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4387152972","https://openalex.org/I4405256580"]},{"id":"https://openalex.org/I4405256580","display_name":"Universit\u00e9 Marie et Louis Pasteur","ror":"https://ror.org/04asdee31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405256580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dombry, Clement","raw_affiliation_strings":["CNRS , LmB (UMR 6623 ) , F-25000 Besan\u00e7on , France","Universit\u00e9 Marie et Louis Pasteur ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS , LmB (UMR 6623 ) , F-25000 Besan\u00e7on , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4387152972"]},{"raw_affiliation_string":"Universit\u00e9 Marie et Louis Pasteur ,","institution_ids":["https://openalex.org/I4405256580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066398937","display_name":"Jean\u2010Jil Duchamps","orcid":"https://orcid.org/0000-0002-3823-1686","observed_orcids":["https://orcid.org/0000-0002-3823-1686"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4387152972","display_name":"Laboratoire de Math\u00e9matiques de Besan\u00e7on","ror":"https://ror.org/04nrhwg12","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4387152972","https://openalex.org/I4405256580"]},{"id":"https://openalex.org/I4405256580","display_name":"Universit\u00e9 Marie et Louis Pasteur","ror":"https://ror.org/04asdee31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405256580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Duchamps, Jean-Jil","raw_affiliation_strings":["CNRS , LmB (UMR 6623 ) , F-25000 Besan\u00e7on , France","Universit\u00e9 Marie et Louis Pasteur ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS , LmB (UMR 6623 ) , F-25000 Besan\u00e7on , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4387152972"]},{"raw_affiliation_string":"Universit\u00e9 Marie et Louis Pasteur ,","institution_ids":["https://openalex.org/I4405256580"]}]}],"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":2,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.20280000567436218,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.20280000567436218,"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/T10136","display_name":"Statistical Methods and Inference","score":0.12080000340938568,"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":0.11400000005960464,"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/decision-tree-ensembles","display_name":"decision tree ensembles","score":0.8059999942779541},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9639999866485596},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"gradient boosting","score":0.9959999918937683},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"reproducing kernel Hilbert space","score":0.9919999837875366},{"id":"https://openalex.org/keywords/random-partitions","display_name":"random partitions","score":0.6690000295639038},{"id":"https://openalex.org/keywords/kernel-pca","display_name":"kernel principal component analysis","score":0.972000002861023},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.9330000281333923}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.6970999836921692},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4869000017642975},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.37459999322891235},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C134517425","wikidata":"https://www.wikidata.org/wiki/Q16000131","display_name":"Kernel embedding of distributions","level":4,"score":0.3716999888420105},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.27799999713897705},{"id":"https://openalex.org/C195699287","wikidata":"https://www.wikidata.org/wiki/Q7915722","display_name":"Variable kernel density estimation","level":4,"score":0.27720001339912415},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26010000705718994},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2776839635","wikidata":"https://www.wikidata.org/wiki/Q14942679","display_name":"Random tree","level":4,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2512.00397","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00397","pdf_url":"https://arxiv.org/pdf/2512.00397","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":"pmh:oai:HAL:hal-05388496v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05388496v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2512.00397","doi":"https://doi.org/10.48550/arxiv.2512.00397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.00397","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:2512.00397","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00397","pdf_url":"https://arxiv.org/pdf/2512.00397","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416936451.pdf","grobid_xml":"https://content.openalex.org/works/W4416936451.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1484867920","https://openalex.org/W1545761024","https://openalex.org/W1565176583","https://openalex.org/W1875028359","https://openalex.org/W1986280275","https://openalex.org/W2035446310","https://openalex.org/W2051922388","https://openalex.org/W2068221105","https://openalex.org/W2070493638","https://openalex.org/W2088883866","https://openalex.org/W2157395790","https://openalex.org/W2162387923","https://openalex.org/W2216946510","https://openalex.org/W2295598076","https://openalex.org/W2418306335","https://openalex.org/W2884147779","https://openalex.org/W2911964244","https://openalex.org/W2987201163","https://openalex.org/W3040192017","https://openalex.org/W3141455185","https://openalex.org/W3158981470","https://openalex.org/W4232478844","https://openalex.org/W4245623693","https://openalex.org/W4300982581","https://openalex.org/W4312072403","https://openalex.org/W4319049461","https://openalex.org/W4388630546"],"related_works":["https://openalex.org/W1875028359","https://openalex.org/W3118230046","https://openalex.org/W6976940928","https://openalex.org/W7161068891","https://openalex.org/W7097512038","https://openalex.org/W2949373041","https://openalex.org/W7024935943","https://openalex.org/W4391556306","https://openalex.org/W2934465633","https://openalex.org/W3043958352"],"abstract_inverted_index":{"Random":[0,78,90,149,200],"Forests":[1],"and":[2,84,86,131,133,163],"Gradient":[3,126],"Boosting":[4,127],"are":[5,28,167],"among":[6],"the":[7,20,62,76,97,122,148,161,164,174,184,199,205],"most":[8],"effective":[9],"algorithms":[10],"for":[11,44,173],"supervised":[12],"learning":[13],"on":[14,55,61,142,198],"tabular":[15],"data.":[16],"Both":[17],"belong":[18],"to":[19,121,138],"class":[21],"of":[22,75,100,113,125,155,178,187,207],"tree-based":[23,179],"ensemble":[24,114,208],"methods,":[25],"where":[26],"predictions":[27],"obtained":[29],"by":[30,66,129,147,190],"aggregating":[31],"many":[32],"randomized":[33,67],"regression":[34,68],"trees.":[35,69],"In":[36],"this":[37,107,119,156,188],"paper,":[38],"we":[39,182],"develop":[40],"a":[41,89,101,110,139,143,170,192,214],"theoretical":[42,171],"framework":[43,157],"analyzing":[45],"such":[46],"methods":[47],"through":[48],"Reproducing":[49],"Kernel":[50],"Hilbert":[51,144],"Spaces":[52],"(RKHSs)":[53],"constructed":[54],"tree":[56],"ensembles":[57],"--":[58],"more":[59],"precisely,":[60],"random":[63],"partitions":[64],"generated":[65],"We":[70,116],"establish":[71],"fundamental":[72],"analytical":[73],"properties":[74],"resulting":[77],"Forest":[79,91,150,201],"kernel,":[80,202],"including":[81],"boundedness,":[82],"continuity,":[83],"universality,":[85],"show":[87],"that":[88,135,159],"predictor":[92],"can":[93],"be":[94],"characterized":[95],"as":[96,210,212],"unique":[98],"minimizer":[99],"penalized":[102],"empirical":[103,176],"risk":[104],"functional":[105],"in":[106],"RKHS,":[108],"providing":[109],"variational":[111],"interpretation":[112],"learning.":[115],"further":[117],"extend":[118],"perspective":[120],"continuous-time":[123],"formulation":[124],"introduced":[128],"Dombry":[130],"Duchamps,":[132],"demonstrate":[134],"it":[136],"corresponds":[137],"gradient":[140],"flow":[141],"manifold":[145],"induced":[146],"RKHS.":[151],"A":[152],"key":[153],"feature":[154],"is":[158],"both":[160],"kernel":[162,193],"RKHS":[165],"geometry":[166],"data-dependent,":[168],"offering":[169],"explanation":[172],"strong":[175],"performance":[177],"ensembles.":[180],"Finally,":[181],"illustrate":[183],"practical":[185],"potential":[186],"approach":[189],"introducing":[191],"principal":[194],"component":[195],"analysis":[196],"built":[197],"which":[203],"enhances":[204],"interpretability":[206],"models,":[209],"well":[211],"GVI,":[213],"new":[215],"geometric":[216],"variable":[217],"importance":[218],"criterion.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-03T00:00:00"}