Composite Functional Gradient Learning of Generative Adversarial Models
arXiv:1801.06309
Abstract
This paper first presents a theory for generative adversarial methods that does not rely on the traditional minimax formulation. It shows that with a strong discriminator, a good generator can be learned so that the KL divergence between the distributions of real data and generated data improves after each functional gradient step until it converges to zero. Based on the theory, we propose a new stable generative adversarial method. A theoretical insight into the original GAN from this new viewpoint is also provided. The experiments on image generation show the effectiveness of our new method.
ICML 2018
References in corpus (10)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Unrolled Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
- Least Squares Generative Adversarial Networks
- AdaGAN: Boosting Generative Models
- Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models