GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
Machine Learning
2016-11-16 v1 Machine Learning
Abstract
Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are not differentiable with respect to the distribution parameters. This problem can be avoided by using the Gumbel-softmax distribution, which is a continuous approximation to a multinomial distribution parameterized in terms of the softmax function. In this work, we evaluate the performance of GANs based on recurrent neural networks with Gumbel-softmax output distributions in the task of generating sequences of discrete elements.
Keywords
Cite
@article{arxiv.1611.04051,
title = {GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution},
author = {Matt J. Kusner and José Miguel Hernández-Lobato},
journal= {arXiv preprint arXiv:1611.04051},
year = {2016}
}