Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting
This provides an incremental improvement for researchers working on generative models with one-dimensional data.
The paper tackles the problem of improving Wasserstein GANs for one-dimensional outputs by identifying a class of summable function decompositions suitable for critics, showing that Taylor and Fourier series belong to this class and outperform standard GAN approaches.
Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution. Instead of explicitly computing these probabilities, GANs learn a generator that can match the given probabilistic source. This paper looks particularly at this matching capability in the context of problems with one-dimensional outputs. We identify a class of function decompositions with properties that make them well suited to the critic role in a leading approach to GANs known as Wasserstein GANs. We show that Taylor and Fourier series decompositions belong to our class, provide examples of these critics outperforming standard GAN approaches, and suggest how they can be scaled to higher dimensional problems in the future.