Show simple item record

dc.contributor.authorBeji, Céline
dc.contributor.authorBenhamou, Éric
dc.contributor.authorBon, Michaël
dc.contributor.authorYger, Florian
dc.contributor.authorAtif, Jamal
dc.date.accessioned2021-01-15T09:27:21Z
dc.date.available2021-01-15T09:27:21Z
dc.date.issued2020
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/21516
dc.language.isoenen
dc.subjectMachine Learningen
dc.subject.ddc005en
dc.titleEstimating Individual Treatment Effects throughCausal Populations Identificationen
dc.typeCommunication / Conférence
dc.description.abstractenEstimating the Individual Treatment Effect from observational data, defined as the difference between outcomes with and without treatment or intervention, while observing just one of both, is a challenging problems in causal learning. In this paper, we formulate this problem as an inference from hidden variables and enforce causal constraints based on a model of four exclusive causal populations. We propose a new version of the EM algorithm, coined as Expected-Causality-Maximization (ECM) algorithm and provide hints on its convergence under mild conditions. We compare our algorithm to baseline methods on synthetic and real-world data and discuss its performances.en
dc.subject.ddclabelProgrammation, logiciels, organisation des donnéesen
dc.relation.conftitle28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020)en
dc.relation.confdate2020-10
dc.relation.confcityBruggesen
dc.relation.confcountryBelgiumen
dc.relation.forthcomingnonen
dc.description.ssrncandidatenonen
dc.description.halcandidateouien
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2021-01-15T09:21:51Z
hal.person.labIds989
hal.person.labIds989
hal.person.labIds115536
hal.person.labIds989
hal.person.labIds989
hal.identifierhal-03111153*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record