Learning to Generate Samples from Noise through Infusion Training
This addresses the challenge of efficient sample generation for machine learning applications, but it appears incremental as it builds on existing generative modeling techniques.
The paper tackles the problem of generating samples from noise by learning a generative model as a Markov chain transition operator that denoises noise into target distribution samples, achieving competitive results with Generative Adversarial Nets in a small number of steps.
In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. The novel training procedure to learn this progressive denoising operation involves sampling from a slightly different chain than the model chain used for generation in the absence of a denoising target. In the training chain we infuse information from the training target example that we would like the chains to reach with a high probability. The thus learned transition operator is able to produce quality and varied samples in a small number of steps. Experiments show competitive results compared to the samples generated with a basic Generative Adversarial Net