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 for image generation on MNSIT.
@article{arxiv.1811.06763,
title = {Entropy-regularized Optimal Transport Generative Models},
author = {Dong Liu and Minh Thành Vu and Saikat Chatterjee and Lars K. Rasmussen},
journal= {arXiv preprint arXiv:1811.06763},
year = {2019}
}