How Well Do WGANs Estimate the Wasserstein Metric?
This addresses the reliability of WGANs for researchers and practitioners in generative modeling, highlighting a trade-off between metric estimation and generative performance, which is incremental as it builds on existing WGAN methods.
The paper investigates how well Wasserstein Generative Adversarial Networks (WGANs) estimate the Wasserstein metric, finding that the c-transform formulation improves metric accuracy but surprisingly underperforms in generative tasks.
Generative modelling is often cast as minimizing a similarity measure between a data distribution and a model distribution. Recently, a popular choice for the similarity measure has been the Wasserstein metric, which can be expressed in the Kantorovich duality formulation as the optimum difference of the expected values of a potential function under the real data distribution and the model hypothesis. In practice, the potential is approximated with a neural network and is called the discriminator. Duality constraints on the function class of the discriminator are enforced approximately, and the expectations are estimated from samples. This gives at least three sources of errors: the approximated discriminator and constraints, the estimation of the expectation value, and the optimization required to find the optimal potential. In this work, we study how well the methods, that are used in generative adversarial networks to approximate the Wasserstein metric, perform. We consider, in particular, the $c$-transform formulation, which eliminates the need to enforce the constraints explicitly. We demonstrate that the $c$-transform allows for a more accurate estimation of the true Wasserstein metric from samples, but surprisingly, does not perform the best in the generative setting.