Selective Sampling and Mixture Models in Generative Adversarial Networks

Abstract

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.

5pages, 3 figures

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Generating Videos with Scene Dynamics
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Towards Principled Methods for Training Generative Adversarial Networks
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Least Squares Generative Adversarial Networks
• Semi-supervised Conditional GANs
• Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
• Imitating Driver Behavior with Generative Adversarial Networks