University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > WGAN and Optimal Transport

WGAN and Optimal Transport

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Alessandro Davide Ialongo.

Abstract

Optimal transport metrics are methods of comparing probability distributions, and are increasingly used in machine learning. We’ll give a general overview of these metrics, and discuss some of the statistical and computational issues with them when applying them in machine learning problems. The second part of the reading group will focus in on the Kantorovich-Rubenstein duality of Wasserstein distance and the Wasserstein GAN , a generative model introduced earlier this year that claims to fix some of the training difficulties associated with GANs, using an optimal transport distance in its training objective.

Recommended Reading

There is no required reading, although the WGAN paper (http://proceedings.mlr.press/v70/arjovsky17a/arjovsky17a.pdf) contains useful background material.

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity