Show simple item record

hal.structure.identifier
dc.contributor.authorClertant, Matthieu
hal.structure.identifier
dc.contributor.authorSokolovska, Nataliya
hal.structure.identifierLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
dc.contributor.authorChevaleyre, Yann
hal.structure.identifierInformatique, Biologie Intégrative et Systèmes Complexes [IBISC]
dc.contributor.authorHanczar, Blaise
dc.date.accessioned2020-02-03T14:44:08Z
dc.date.available2020-02-03T14:44:08Z
dc.date.issued2019
dc.identifier.issn2640-3498
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/20517
dc.language.isoenen
dc.subjectsequential decisionsen
dc.subject.ddc006.3en
dc.titleInterpretable Cascade Classifiers with Abstentionen
dc.typeCommunication / Conférence
dc.description.abstractenIn many prediction tasks such as medical diagnostics, sequential decisions are crucial to provide optimal individual treatment. Budget in real-life applications is always limited, and it can represent any limited resource such as time, money, or side effects of medications. In this contribution, we develop a POMDP-based framework to learn cost-sensitive heterogeneous cascading systems. We provide both the theoretical support for the introduced approach and the intuition behind it. We evaluate our novel method on some standard benchmarks, and we discuss how the learned models can be interpreted by human experts.en
dc.identifier.citationpages89:2312-2320en
dc.relation.ispartoftitle22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)en
dc.relation.ispartofeditorChaudhuri, Kamalika
dc.relation.ispartofeditorSugiyama, Masashi
dc.relation.ispartofpublnameProceedings of Machine Learning Researchen
dc.relation.ispartofdate2019
dc.contributor.countryeditoruniversityotherFRANCE
dc.subject.ddclabelIntelligence artificielleen
dc.relation.conftitle22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)en
dc.relation.confdate2019-04
dc.relation.confcityNaha, Okinawaen
dc.relation.confcountryJapanen
dc.relation.forthcomingnonen
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2020-02-01T14:15:44Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record