Designing GANs: A Likelihood Ratio Approach

Abstract

We are interested in the design of generative networks. The training of these mathematical structures is mostly performed with the help of adversarial (min-max) optimization problems. We propose a simple methodology for constructing such problems assuring, at the same time, consistency of the corresponding solution. We give characteristic examples developed by our method, some of which can be recognized from other applications, and some are introduced here for the first time. We present a new metric, the likelihood ratio, that can be employed online to examine the convergence and stability during the training of different Generative Adversarial Networks (GANs). Finally, we compare various possibilities by applying them to well-known datasets using neural networks of different configurations and sizes.

Accepted to "The Joint International Conference on Neural Networks (IJCNN 2021)"

References in corpus (6)

• Generative Adversarial Networks: An Overview
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Energy-based Generative Adversarial Network
• Approximation and Convergence Properties of Generative Adversarial Learning
• Lipschitz Generative Adversarial Nets
• $(f,\Gamma )$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics

Cited by in corpus (2)

• Image Restoration from Parametric Transformations using Generative Models
• Image De-Quantization Using Generative Models as Priors