Entropy-regularized Optimal Transport Generative Models
Dong Liu, Minh Thành Vu, Saikat Chatterjee, Lars Kildehoj Rasmussen · 2019
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One uses EOT cost directly in an one-shot optimization problem and the other uses EOT cost iteratively in an adversarial game. The proposed generative models show improved performance over contemporary models on scores of sample based test.