On Duality Gap as a Measure for Monitoring GAN Training

by   Sahil Sidheekh, et al.

Generative adversarial network (GAN) is among the most popular deep learning models for learning complex data distributions. However, training a GAN is known to be a challenging task. This is often attributed to the lack of correlation between the training progress and the trajectory of the generator and discriminator losses and the need for the GAN's subjective evaluation. A recently proposed measure inspired by game theory - the duality gap, aims to bridge this gap. However, as we demonstrate, the duality gap's capability remains constrained due to limitations posed by its estimation process. This paper presents a theoretical understanding of this limitation and proposes a more dependable estimation process for the duality gap. At the crux of our approach is the idea that local perturbations can help agents in a zero-sum game escape non-Nash saddle points efficiently. Through exhaustive experimentation across GAN models and datasets, we establish the efficacy of our approach in capturing the GAN training progress with minimal increase to the computational complexity. Further, we show that our estimate, with its ability to identify model convergence/divergence, is a potential performance measure that can be used to tune the hyperparameters of a GAN.


page 8

page 15


Characterizing GAN Convergence Through Proximal Duality Gap

Despite the accomplishments of Generative Adversarial Networks (GANs) in...

A Convex Duality Framework for GANs

Generative adversarial network (GAN) is a minimax game between a generat...

Efficient low-thrust trajectory data generation based on generative adversarial network

Deep learning-based techniques have been introduced into the field of tr...

Fictitious GAN: Training GANs with Historical Models

Generative adversarial networks (GANs) are powerful tools for learning g...

Evaluating GANs via Duality

Generative Adversarial Networks (GANs) have shown great results in accur...

Residual-Aided End-to-End Learning of Communication System without Known Channel

Leveraging powerful deep learning techniques, the end-to-end (E2E) learn...

Please sign up or login with your details

Forgot password? Click here to reset