Improving Generalization and Stability of Generative Adversarial Networks

Abstract

Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the generalization of GANs in practical settings. We show that discriminators trained on discrete datasets with the original GAN loss have poor generalization capability and do not approximate the theoretically optimal discriminator. We propose a zero-centered gradient penalty for improving the generalization of the discriminator by pushing it toward the optimal discriminator. The penalty guarantees the generalization and convergence of GANs. Experiments on synthetic and large scale datasets verify our theoretical analysis.

ICLR 2019

Cited by in corpus (10)

• GNPassGAN: Improved Generative Adversarial Networks For Trawling Offline Password Guessing
• Unsupervised anomaly localization using VAE and beta-VAE
• Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
• Bounds all around: training energy-based models with bidirectional bounds
• From Shadow Segmentation to Shadow Removal
• Adversarial Imitation Learning with Trajectorial Augmentation and Correction
• Slimmable Generative Adversarial Networks
• Semantic Preserving Generative Adversarial Models
• Improving Generative Adversarial Networks with Local Coordinate Coding
• Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck