English

Designing GANs: A Likelihood Ratio Approach

Machine Learning 2021-07-16 v3 Machine Learning

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.

Keywords

Cite

@article{arxiv.2002.00865,
  title  = {Designing GANs: A Likelihood Ratio Approach},
  author = {Kalliopi Basioti and George V. Moustakides},
  journal= {arXiv preprint arXiv:2002.00865},
  year   = {2021}
}

Comments

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

R2 v1 2026-06-23T13:29:30.365Z