wasserstein loss
Wasserstein loss, also known as Earth Mover's Distance (EMD) loss, is a metric used to measure the dissimilarity between two probability distributions. It quantifies the minimum amount of work needed to transform one distribution into another, considering the cost of moving mass from one point to another. By minimizing Wasserstein loss, a model aims to bring the generated distribution closer to the target distribution, resulting in improved performance in tasks such as generative adversarial networks (GANs) and image synthesis.
Requires login.