Fréchet Mean Computation in Graph Space through Projected Block Gradient Descent
dc.contributor.author | Boria, Nicolas
HAL ID: 21013 ORCID: 0000-0002-0548-4257 | |
dc.contributor.author | Negrevergne, Benjamin
HAL ID: 172154 ORCID: 0000-0002-7074-8167 | |
dc.contributor.author | Yger, Florian
HAL ID: 17768 ORCID: 0000-0002-7182-8062 | |
dc.date.accessioned | 2020-11-04T13:36:03Z | |
dc.date.available | 2020-11-04T13:36:03Z | |
dc.date.issued | 2020 | |
dc.identifier.uri | https://basepub.dauphine.fr/handle/123456789/21185 | |
dc.language.iso | en | en |
dc.subject | Graph space | |
dc.subject.ddc | 005 | en |
dc.title | Fréchet Mean Computation in Graph Space through Projected Block Gradient Descent | |
dc.type | Communication / Conférence | |
dc.description.abstracten | A fundamental concept in statistics is the concept of Fréchet sample mean. While its computation is a simple task in Euclidian space, the same does not hold for less structured spaces such as the space of graphs, where concepts of distance or mid-point can be hard to compute. We present some work in progress regarding new distance measures and new algorithms to compute the Fréchet mean in the space of Graphs. | |
dc.identifier.urlsite | https://hal-normandie-univ.archives-ouvertes.fr/hal-02895832 | |
dc.subject.ddclabel | Programmation, logiciels, organisation des données | en |
dc.relation.conftitle | 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020) | |
dc.relation.confdate | 2020-10 | |
dc.relation.confcity | Bruges | |
dc.relation.confcountry | FRANCE | |
dc.relation.forthcoming | non | en |
dc.description.ssrncandidate | non | |
dc.description.halcandidate | non | |
dc.description.readership | recherche | |
dc.description.audience | International | |
dc.date.updated | 2021-01-12T14:41:17Z |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |