Show simple item record

dc.contributor.authorBelahcene, Khaled
HAL ID: 5889
dc.contributor.authorSokolovska, Nataliya
dc.contributor.authorChevaleyre, Yann
dc.contributor.authorZucker, Jean-Daniel
HAL ID: 9387
ORCID: 0000-0002-5597-7922
dc.date.accessioned2020-10-23T10:02:43Z
dc.date.available2020-10-23T10:02:43Z
dc.date.issued2020
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/21150
dc.language.isoenen
dc.subjectRegularization
dc.subjectinterpretable models
dc.subjectinteger models
dc.subject.ddc004en
dc.titleLearning Interpretable Models using Soft Integrity Constraints
dc.typeCommunication / Conférence
dc.description.abstractenInteger models are of particular interest for applications where predictive models are supposed not only to be accurate but also interpretable to human experts. We introduce a novel penalty term called Facets whose primary goal is to favour integer weights. Our theoretical results illustrate the behaviour of the proposed penalty term: for small enough weights, the Facets matches the L 1 penalty norm, and as the weights grow, it approaches the L 2 regulariser. We provide the proximal operator associated with the proposed penalty term, so that the regularized empirical risk minimiser can be computed efficiently. We also introduce the Strongly Convex Facets, and discuss its theoretical properties. Our numerical results show that while achieving the state-of-the-art accuracy, optimisation of a loss function penalised by the proposed Facets penalty term leads to a model with a significant number of integer weights.
dc.identifier.urlsitehttps://hal.archives-ouvertes.fr/hal-02944833
dc.subject.ddclabelInformatique généraleen
dc.relation.conftitle12th Asian Conference on Machine Learning (ACML 2020)
dc.relation.confdate2020-11
dc.relation.confcityBangkok
dc.relation.confcountryTHAILAND
dc.relation.forthcomingnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2020-12-17T09:31:50Z


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record