Learning GANs in Simultaneous Game Using Sinkhorn With Positive Features

Learning GANs in Simultaneous Game Using Sinkhorn With Positive Features

Show other versions (1)

Entropy regularized optimal transport (EOT) distance and its symmetric normalization, known as the Sinkhorn divergence, offer smooth and continuous metrized weak-convergence distance metrics. They have excellent geometric properties and are useful to compare probability distributions in some generat...

Deskribapen osoa

Xehetasun bibliografikoak
Egile Nagusiak: Risman Adnan, Muchlisin Adi Saputra, Junaidillah Fadlil, Martianus Frederic Ezerman, Muhamad Iqbal, Tjan Basaruddin
Formatua: Artikulua
Hizkuntza:English
Argitaratua: IEEE 2021-01-01
Saila:IEEE Access
Gaiak:
Entropy regularized optimal transport
generative adversarial network
Sinkhorn divergence
Sinkhorn with positive features
Sarrera elektronikoa:https://ieeexplore.ieee.org/document/9570346/

Internet

https://ieeexplore.ieee.org/document/9570346/

Antzeko izenburuak