GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
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...
Saved in:
Main Authors | , |
---|---|
Format | Journal Article |
Language | English |
Published |
12.11.2016
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | 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. |
---|---|
DOI: | 10.48550/arxiv.1611.04051 |