Selective Sampling and Mixture Models in Generative Adversarial Networks
This work addresses the challenge of selective sampling from mixture distributions in generative modeling, which is an incremental improvement for researchers in machine learning.
The paper tackles the problem of representing distinct components of a mixture distribution in generative adversarial networks by proposing a multi-generator extension where each generator targets a unique component, and demonstrates its feasibility analytically and on the MNIST dataset with basic MLP models.
In this paper, we propose a multi-generator extension to the adversarial training framework, in which the objective of each generator is to represent a unique component of a target mixture distribution. In the training phase, the generators cooperate to represent, as a mixture, the target distribution while maintaining distinct manifolds. As opposed to traditional generative models, inference from a particular generator after training resembles selective sampling from a unique component in the target distribution. We demonstrate the feasibility of the proposed architecture both analytically and with basic Multi-Layer Perceptron (MLP) models trained on the MNIST dataset.