| Title | Generative Adversarial Networks: A Likelihood Ratio Approach |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Basioti, Kalliopi, Moustakides, George V. |
| Conference Name | 2021 International Joint Conference on Neural Networks (IJCNN) |
| Keywords | character recognition, Complexity theory, Generative Adversarial Learning, generative adversarial networks, Generative Networks, Likelihood Ratio, Measurement, Metrics, Neural networks, pubcrawl, resilience, Resiliency, Scalability, Tools, Training |
| 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. |
| DOI | 10.1109/IJCNN52387.2021.9533584 |
| Citation Key | basioti_generative_2021 |
Generative Adversarial Networks: A Likelihood Ratio Approach