papers AI Learner
The Github is limit! Click to go to the new site.

GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution

2016-11-12
Matt J. Kusner, José Miguel Hernández-Lobato

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1611.04051

PDF

https://arxiv.org/pdf/1611.04051


Similar Posts

Comments