The Benefits of Pairwise Discriminators for Adversarial Training

Abstract

Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a sub-optimal discriminator can still drive the two apart. Absent additional regularization, the instability can manifest itself as a never-ending game. In this paper, we introduce a family of objectives by leveraging pairwise discriminators, and show that only the generator needs to converge. The alignment, if achieved, would be preserved with any discriminator. We provide sufficient conditions for local convergence; characterize the capacity balance that should guide the discriminator and generator choices; and construct examples of minimally sufficient discriminators. Empirically, we illustrate the theory and the effectiveness of our approach on synthetic examples. Moreover, we show that practical methods derived from our approach can better generate higher-resolution images.

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Which Training Methods for GANs do actually Converge?
• Generative Moment Matching Networks
• Training generative neural networks via Maximum Mean Discrepancy optimization
• The Numerics of GANs
• On Relativistic $f$-Divergences