Learning latent permutations with Gumbel-Sinkhorn networks
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper in...
Príomhchruthaitheoirí: | Mena, G, Snoek, J, Linderman, S, Belanger, D |
---|---|
Formáid: | Conference item |
Teanga: | English |
Foilsithe / Cruthaithe: |
OpenReview
2018
|
Míreanna comhchosúla
-
Learning GANs in simultaneous game using Sinkhorn with positive features
de réir: Risman Adnan, et al.
Foilsithe / Cruthaithe: (2022) -
Learning GANs in Simultaneous Game Using Sinkhorn With Positive Features
de réir: Risman Adnan, et al.
Foilsithe / Cruthaithe: (2021-01-01) -
Equivalence between the Fitness-Complexity and the Sinkhorn-Knopp algorithms
de réir: D Mazzilli, et al.
Foilsithe / Cruthaithe: (2024-01-01) -
Distance-weighted Sinkhorn loss for Alzheimer’s disease classification
de réir: Zexuan Wang, et al.
Foilsithe / Cruthaithe: (2024-03-01) -
Overrelaxed Sinkhorn–Knopp Algorithm for Regularized Optimal Transport
de réir: Alexis Thibault, et al.
Foilsithe / Cruthaithe: (2021-04-01)