Show simple item record

X-Ray Sobolev Variational Auto-Encoders

hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorTurinici, Gabriel
HAL ID: 16
ORCID: 0000-0003-2713-006X
dc.date.accessioned2019-12-19T12:39:57Z
dc.date.available2019-12-19T12:39:57Z
dc.date.issued2019
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/20349
dc.language.isoenen
dc.subjectmachine learningen
dc.subjectvariational auto-encoderen
dc.subjectneural networken
dc.subjectdeep learningen
dc.subject.ddc515en
dc.titleX-Ray Sobolev Variational Auto-Encodersen
dc.typeDocument de travail / Working paper
dc.description.abstractenThe quality of the generative models (Generative adversarial networks, Variational Auto-Encoders, ...) depends heavily on the choice of a good probability distance. However some popular metrics lack convenient properties such as (geodesic) convexity, fast evaluation and so on. To address these shortcomings, we introduce a class of distances that have built-in convexity. We investigate the relationship with some known paradigms (sliced distances, reproducing kernel Hilbert spaces, energy distances). The distances are shown to posses fast implementations and are included in an adapted Variational Auto-Encoder termed X-ray Sobolev Variational Auto-Encoder (XS-VAE) which produces good quality results on standard generative datasets.en
dc.publisher.nameCahier de recherche CEREMADE, Université Paris-Dauphineen
dc.publisher.cityParisen
dc.identifier.citationpages26en
dc.relation.ispartofseriestitleCahier de recherche CEREMADE, Université Paris-Dauphineen
dc.identifier.urlsitehttps://hal.archives-ouvertes.fr/hal-02387084en
dc.subject.ddclabelAnalyseen
dc.identifier.citationdate2019-11
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.date.updated2019-12-19T12:38:03Z
hal.author.functionaut


Files in this item

Thumbnail
Name:
1911.13135(1).pdf
Size:
840.9Kb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record