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

11/12/2016
by   Matt J. Kusner, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset