Wasserstein GAN
A Wasserstein GAN is a generative adversarial network that uses a critic and a Wasserstein-based objective to compare generated and real-data distributions.
Learn Generative AI with PyTorch
A GAN variant that uses the Wasserstein distance as its training objective to improve stability and provide a more informative critic score.
- How it is used
- Stabilizes GAN training by replacing binary cross-entropy with Wasserstein distance and adding gradient-based constraint enforcement.
- How deep it goes
- Explains the critic, Lipschitz requirement, interpolation, gradient calculation, and penalty, without deriving the distance mathematically.
- Examples
- Demonstrates conditional face generation with or without eyeglasses using labeled noise, interpolated images, and critic scores.
- What you can do after
- Build a conditional WGAN with gradient penalty for labeled face generation and calculate Wasserstein loss and gradient penalty.
Read how Learn Generative AI with PyTorch explains Wasserstein GAN →
Inside Deep Learning: Math, Algorithms, Models
A GAN variant that uses a Wasserstein-based objective to improve training behavior and stability.
- How it is used
- Uses a Wasserstein-based GAN training approach to reduce mode collapse.
- How deep it goes
- Explains discriminator behavior and the generator loss, but leaves the Wasserstein derivation out.
- What you can do after
- Understand the generator objective as the negated discriminator score on generated samples.
Read how Inside Deep Learning: Math, Algorithms, Models explains Wasserstein GAN →
Also covered in
What to know first
- discriminatorA discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.
- generatorA generator is a computational component or construct that produces data or values from inputs, representations, context, or specified constraints.
- generative adversarial networkA generative adversarial network is a generative model in which a generator and a discriminator are trained adversarially, with the generator learning to produce samples resembling data from a target distribution.
- objective functionAn objective function is a mathematical function that assigns values to candidate solutions or parameter settings, which an optimization procedure seeks to minimize or maximize.
Related concepts
- Wasserstein distanceuses · Wasserstein distance is a distance between probability distributions defined by the minimum cost of transporting probability mass between them under a specified ground distance.
- generative adversarial networkalternative to · A generative adversarial network is a generative model in which a generator and a discriminator are trained adversarially, with the generator learning to produce samples resembling data from a target distribution.
- mode collapseaddresses · Mode collapse is a generative-model failure in which outputs concentrate on a narrow range of patterns and fail to represent the diversity of the target distribution.
- discriminatorcontrasts with · A discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.
- regularizationuses · Regularization is a modeling technique that constrains learning or penalizes model complexity to discourage overfitting and improve generalization.
- gradient penaltyused by · A gradient penalty is a regularization loss term that penalizes undesirable gradients during model optimization.
Questions about Wasserstein GAN
What is Wasserstein GAN?
A Wasserstein GAN is a generative adversarial network that uses a critic and a Wasserstein-based objective to compare generated and real-data distributions.
Which Manning books explain Wasserstein GAN?
Learn Generative AI with PyTorch and Inside Deep Learning: Math, Algorithms, Models.
What should I know before learning Wasserstein GAN?
Manning books that teach Wasserstein GAN usually introduce discriminator, generator, generative adversarial network and objective function first.
What is the difference between Wasserstein GAN and generative adversarial network?
A Wasserstein GAN is a generative adversarial network that uses a critic and a Wasserstein-based objective to compare generated and real-data distributions. A generative adversarial network is a generative model in which a generator and a discriminator are trained adversarially, with the generator learning to produce samples resembling data from a target distribution.
What is Wasserstein GAN also called?
Wasserstein GAN is also called WGAN.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

