On Characterizing GAN Convergence Through Proximal Duality Gap

Abstract

Despite the accomplishments of Generative Adversarial Networks (GANs) in modeling data distributions, training them remains a challenging task. A contributing factor to this difficulty is the non-intuitive nature of the GAN loss curves, which necessitates a subjective evaluation of the generated output to infer training progress. Recently, motivated by game theory, duality gap has been proposed as a domain agnostic measure to monitor GAN training. However, it is restricted to the setting when the GAN converges to a Nash equilibrium. But GANs need not always converge to a Nash equilibrium to model the data distribution. In this work, we extend the notion of duality gap to proximal duality gap that is applicable to the general context of training GANs where Nash equilibria may not exist. We show theoretically that the proximal duality gap is capable of monitoring the convergence of GANs to a wider spectrum of equilibria that subsumes Nash equilibria. We also theoretically establish the relationship between the proximal duality gap and the divergence between the real and generated data distributions for different GAN formulations. Our results provide new insights into the nature of GAN convergence. Finally, we validate experimentally the usefulness of proximal duality gap for monitoring and influencing GAN training.

References in corpus (15)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Self-Attention Generative Adversarial Networks
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Assessing Generative Models via Precision and Recall
• A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
• AdaGAN: Boosting Generative Models
• On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games
• Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games
• Convergence of Learning Dynamics in Stackelberg Games
• A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
• A domain agnostic measure for monitoring and evaluating GANs
• Skill Rating for Generative Models
• TorchGAN: A Flexible Framework for GAN Training and Evaluation