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).

[img] Text
1611.04051v1.pdf - Accepted version
Access restricted to UCL open access staff until 5 May 2021.

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 > 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