DeepAI AI Chat
Log In Sign Up

Designing GANs: A Likelihood Ratio Approach

by   Kalliopi Basioti, et al.

We are interested in the design of generative adversarial networks. The training of these mathematical structures requires the definition of proper min-max optimization problems. We propose a simple methodology for constructing such problems assuring, at the same time, that they provide the correct answer. We give characteristic examples developed by our method, some of which can be recognized from other applications and some introduced for the first time. We compare various possibilities by applying them to well known datasets using neural networks of different configurations and sizes.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9


Training generative networks using random discriminators

In recent years, Generative Adversarial Networks (GANs) have drawn a lot...

Kernel-Based Training of Generative Networks

Generative adversarial networks (GANs) are designed with the help of min...

Optimizing Shallow Networks for Binary Classification

Data driven classification that relies on neural networks is based on op...

Solving a class of non-convex min-max games using adaptive momentum methods

Adaptive momentum methods have recently attracted a lot of attention for...

Generative Minimization Networks: Training GANs Without Competition

Many applications in machine learning can be framed as minimization prob...

Training Neural Networks for Likelihood/Density Ratio Estimation

Various problems in Engineering and Statistics require the computation o...