Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogates
arXiv:2101.06802
Abstract
We propose a simple but effective modification of the discriminators, namely measure-conditional discriminators, as a plug-and-play module for different GANs. By taking the generated distributions as part of input so that the target optimum for the discriminator is stationary, the proposed discriminator is more robust than the vanilla one. A variant of the measure-conditional discriminator can also handle multiple target distributions, or act as a surrogate model of statistical distances such as KL divergence with applications to transfer learning.
References in corpus (7)
- Conditional Generative Adversarial Nets
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Estimating divergence functionals and the likelihood ratio by convex risk minimization
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- MaskGAN: Better Text Generation via Filling in the______
- Mixed batches and symmetric discriminators for GAN training
- Approximation capability of neural networks on spaces of probability measures and tree-structured domains