Show simple item record

dc.contributor.authorBenhamou, Éric
dc.contributor.authorAtif, Jamal
HAL ID: 15689
dc.contributor.authorLaraki, Rida
HAL ID: 179670
ORCID: 0000-0002-4898-2424
dc.contributor.authorSaltiel, David
dc.date.accessioned2020-11-12T11:07:13Z
dc.date.available2020-11-12T11:07:13Z
dc.date.issued2020
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/21206
dc.language.isoenen
dc.subjectOptimization
dc.subject.ddc006.3en
dc.titleNGO-GM: Natural Gradient Optimization for Graphical Models
dc.typeDocument de travail / Working paper
dc.description.abstractenThis paper deals with estimating model parameters in graphical models. We reformulate it as an information geometric optimization problem and introduce a natural gradient descent strategy that incorporates additional meta parameters. We show that our approach is a strong alternative to the celebrated EM approach for learning in graphical models. Actually, our natural gradient based strategy leads to learning optimal parameters for the final objective function without artificially trying to fit a distribution that may not correspond to the real one. We support our theoretical findings with the question of trend detection in financial markets and show that the learned model performs better than traditional practitioner methods and is less prone to overfitting.
dc.publisher.cityParisen
dc.relation.ispartofseriestitlePreprint Lamsade
dc.identifier.urlsitehttps://hal.archives-ouvertes.fr/hal-02886514
dc.subject.ddclabelIntelligence artificielleen
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2020-12-17T19:08:45Z


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