UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

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

Kusner, MJ; Hernández-Lobato, JM; (2020) GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution. (In press).

[thumbnail of 1611.04051v1.pdf] Text
1611.04051v1.pdf - Accepted version
Access restricted to UCL open access staff until 16 April 2022.

Download (828kB)

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.

Type: Article
Title: GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10088324
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item