{"id":"https://openalex.org/W4394635009","doi":"https://doi.org/10.48550/arxiv.1809.04559","title":"Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms","display_name":"Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms","publication_year":2018,"publication_date":"2018-09-12","ids":{"openalex":"https://openalex.org/W4394635009","doi":"https://doi.org/10.48550/arxiv.1809.04559"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1809.04559","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04559","pdf_url":"https://arxiv.org/pdf/1809.04559","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.04559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055907161","display_name":"Andreea Anghel","orcid":"https://orcid.org/0000-0002-6842-9036","observed_orcids":["https://orcid.org/0000-0002-6842-9036"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anghel, Andreea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241728","display_name":"Nikolaos Papandreou","orcid":"https://orcid.org/0000-0001-6979-2171","observed_orcids":["https://orcid.org/0000-0001-6979-2171"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papandreou, Nikolaos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Parnell, Thomas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parnell, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073957171","display_name":"Alessandro De Palma","orcid":"https://orcid.org/0009-0002-7229-7723","observed_orcids":["https://orcid.org/0009-0002-7229-7723"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Palma, Alessandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007575599","display_name":"Haralampos Pozidis","orcid":"https://orcid.org/0000-0001-5084-6651","observed_orcids":["https://orcid.org/0000-0001-5084-6651"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pozidis, Haralampos","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":43,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9096999764442444,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9096999764442444,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0551999993622303,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.009399999864399433,"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/gradient-boosted-decision-trees","display_name":"gradient boosting decision tree","score":0.9819999933242798},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.8109999895095825},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.7590000033378601},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.8960000276565552},{"id":"https://openalex.org/keywords/lightgbm","display_name":"LightGBM","score":1.0},{"id":"https://openalex.org/keywords/catboost","display_name":"CatBoost","score":0.9919999837875366},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.6850000023841858},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.5360000133514404},{"id":"https://openalex.org/keywords/generalization-performance","display_name":"generalization performance","score":0.7749999761581421},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912134528160095},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7287682890892029},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7193123698234558},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.685240626335144},{"id":"https://openalex.org/C120136583","wikidata":"https://www.wikidata.org/wiki/Q4736414","display_name":"Alternating decision tree","level":5,"score":0.6732932329177856},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.6583454012870789},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.6522238850593567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274780631065369},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5998674631118774},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4639548659324646},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41141220927238464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32945680618286133},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.2491864562034607},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.1893632411956787},{"id":"https://openalex.org/C10229987","wikidata":"https://www.wikidata.org/wiki/Q17083028","display_name":"Incremental decision tree","level":4,"score":0.18801963329315186},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1809.04559","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04559","pdf_url":"https://arxiv.org/pdf/1809.04559","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.1809.04559","doi":"https://doi.org/10.48550/arxiv.1809.04559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.04559","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.04559","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04559","pdf_url":"https://arxiv.org/pdf/1809.04559","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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W3094138326","https://openalex.org/W4310224730"],"abstract_inverted_index":{"Gradient":[0],"boosting":[1],"decision":[2],"trees":[3],"(GBDTs)":[4],"have":[5,94],"seen":[6],"widespread":[7],"adoption":[8],"in":[9,21,147,154,168],"academia,":[10],"industry":[11],"and":[12,117,139,167],"competitive":[13],"data":[14],"science":[15],"due":[16],"to":[17,29,41,96,103,162],"their":[18],"state-of-the-art":[19],"performance":[20,123],"many":[22],"machine":[23],"learning":[24,140],"tasks.":[25,141],"One":[26],"relative":[27],"downside":[28],"these":[30,72,130],"models":[31],"is":[32],"the":[33,42,46,57,81,122,125,145,148],"large":[34],"number":[35,89],"of":[36,49,71,86,90,124,150,156,170],"hyper-parameters":[37],"that":[38],"they":[39,77],"expose":[40],"end-user.":[43],"To":[44],"maximize":[45],"predictive":[47],"power":[48],"GBDT":[50,92],"models,":[51],"one":[52],"must":[53],"either":[54],"manually":[55],"tune":[56],"hyper-parameters,":[58],"or":[59],"utilize":[60],"automated":[61],"techniques":[62],"such":[63,113],"as":[64],"those":[65],"based":[66],"on":[67],"Bayesian":[68],"optimization.":[69],"Both":[70],"approaches":[73],"are":[74],"time-consuming":[75],"since":[76],"involve":[78],"repeatably":[79],"training":[80],"model":[82],"for":[83],"different":[84],"sets":[85],"hyper-parameters.":[87],"A":[88],"software":[91],"packages":[93,131,146],"started":[95],"offer":[97],"GPU":[98,126],"acceleration":[99,127],"which":[100],"can":[101],"help":[102],"alleviate":[104],"this":[105,108],"problem.":[106],"In":[107],"paper,":[109],"we":[110,120,143],"consider":[111],"three":[112],"packages:":[114],"XGBoost,":[115],"LightGBM":[116],"Catboost.":[118],"Firstly,":[119],"evaluate":[121],"provided":[128],"by":[129],"using":[132],"large-scale":[133],"datasets":[134],"with":[135],"varying":[136],"shapes,":[137],"sparsities":[138],"Then,":[142],"compare":[144],"context":[149],"hyper-parameter":[151],"optimization,":[152],"both":[153],"terms":[155,169],"how":[157],"quickly":[158],"each":[159],"package":[160],"converges":[161],"a":[163],"good":[164],"validation":[165],"score,":[166],"generalization":[171],"performance.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}