Caesar AI Atlas

Wasserstein Loss

Caesar AI Atlas Definition

Wasserstein loss is a loss function based on the earth mover’s distance between probability distributions. In generative adversarial networks, it is used to compare generated and real data distributions in a way that can improve training stability.

Other Definitions

Wasserstein Loss Source

One of the loss functions commonly used in generative adversarial networks, based on the earth mover's distance between the distribution of generated data and real data.

Related Terms