{"id":"https://openalex.org/W7160528289","doi":"https://doi.org/10.48550/arxiv.2605.04671","title":"ITBoost: Information-Theoretic Trust for Robust Boosting","display_name":"ITBoost: Information-Theoretic Trust for Robust Boosting","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160528289","doi":"https://doi.org/10.48550/arxiv.2605.04671"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04671","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.2605.04671","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135591251","display_name":"Ye Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047335949","display_name":"Longlong Zhao","orcid":"https://orcid.org/0000-0002-8145-3727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Longlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052686664","display_name":"Diego Garc\u00eda\u2010Gil","orcid":"https://orcid.org/0000-0002-1927-8673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garcia-Gil, Diego","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135546592","display_name":"Jipeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135625216","display_name":"Gangchun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Gangchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016898619","display_name":"Jinxin Chen","orcid":"https://orcid.org/0009-0008-8311-288X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135618535","display_name":"Jinsong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinsong","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/T12535","display_name":"Machine Learning and Data Classification","score":0.6812000274658203,"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":0.6812000274658203,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.23340000212192535,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.01269999984651804,"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/boosting","display_name":"Boosting (machine learning)","score":0.8960000276565552},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6370000243186951},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.5856000185012817},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5593000054359436},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.38690000772476196},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8960000276565552},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5856000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787000060081482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.578499972820282},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5662999749183655},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.38690000772476196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2985999882221222},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04671","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.2605.04671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04671","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/9","score":0.40457847714424133,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Gradient":[0],"boosting":[1,31,155],"remains":[2],"a":[3,129],"strong":[4],"and":[5,121,156],"widely":[6],"used":[7],"method":[8],"for":[9,41,133],"tabular":[10,142,158],"data":[11],"learning,":[12],"but":[13],"its":[14],"performance":[15,164],"often":[16],"degrades":[17],"when":[18],"training":[19],"labels":[20],"are":[21,116,122],"noisy.":[22],"This":[23],"behavior":[24],"is":[25,63],"largely":[26],"related":[27],"to":[28,100],"the":[29,75,95,102],"way":[30],"algorithms":[32],"emphasize":[33],"samples":[34],"with":[35],"large":[36],"gradients,":[37],"without":[38],"explicitly":[39],"accounting":[40],"whether":[42],"such":[43],"errors":[44],"originate":[45],"from":[46,51],"informative":[47],"hard":[48],"cases":[49],"or":[50],"unreliable":[52],"labels.":[53],"We":[54],"address":[55],"this":[56,85],"issue":[57],"by":[58],"reconsidering":[59],"how":[60],"sample":[61],"reliability":[62],"evaluated":[64],"during":[65,124],"boosting.":[66],"Instead":[67],"of":[68,77,104],"relying":[69],"on":[70,84,140,165],"instantaneous":[71],"error,":[72],"we":[73,87,127],"examine":[74],"evolution":[76],"each":[78],"sample's":[79],"residuals":[80],"across":[81],"iterations.":[82],"Based":[83],"insight,":[86],"propose":[88],"Information-Theoretic":[89],"Trust":[90],"Boosting":[91],"(ITBoost),":[92],"which":[93],"uses":[94],"Minimum":[96],"Description":[97],"Length":[98],"principle":[99],"measure":[101],"complexity":[103],"residual":[105,109],"trajectories.":[106],"Samples":[107],"whose":[108],"patterns":[110],"fluctuate":[111],"in":[112,150],"an":[113],"irregular":[114],"manner":[115],"treated":[117],"as":[118],"less":[119],"trustworthy":[120],"down-weighted":[123],"learning.":[125],"Theoretically,":[126],"derive":[128],"tighter":[130],"generalization":[131],"bound":[132],"ITBoost":[134,146],"under":[135],"label":[136],"noise.":[137],"Empirical":[138],"results":[139],"various":[141],"benchmarks":[143],"indicate":[144],"that":[145],"provides":[147],"improved":[148],"robustness":[149],"noisy":[151],"environments":[152],"over":[153],"leading":[154],"deep":[157],"models,":[159],"while":[160],"retaining":[161],"best":[162],"average":[163],"clean":[166],"data.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}