Bayesian GAN
This addresses the challenge of training reliable and diverse generative models for researchers and practitioners in machine learning, offering a novel approach to improve GAN stability and performance.
The paper tackles the problem of mode collapse and instability in GANs by proposing a Bayesian formulation that marginalizes network weights using stochastic gradient Hamiltonian Monte Carlo, resulting in state-of-the-art performance on semi-supervised learning benchmarks like SVHN, CelebA, and CIFAR-10, outperforming methods such as DCGAN and Wasserstein GANs.
Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo to marginalize the weights of the generator and discriminator networks. The resulting approach is straightforward and obtains good performance without any standard interventions such as feature matching, or mini-batch discrimination. By exploring an expressive posterior over the parameters of the generator, the Bayesian GAN avoids mode-collapse, produces interpretable and diverse candidate samples, and provides state-of-the-art quantitative results for semi-supervised learning on benchmarks including SVHN, CelebA, and CIFAR-10, outperforming DCGAN, Wasserstein GANs, and DCGAN ensembles.