University of Cambridge > Talks.cam > Machine Learning @ CUED > On Different Distances Between Distributions and Generative Adversarial Networks

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

On Different Distances Between Distributions and Generative Adversarial Networks

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

If you have a question about this talk, please contact dsu21.

Generative adversarial networks (GANs) are notoriously difficult to train. At the core of it, we show that these problems arise naturally when trying to learn distributions whose support lie in low dimensional manifolds. We show how these problems are consequences of trying to optimize the classical divergences (KL, JSD , etc) between our real and data distribution, and that these are symptoms of a more general phenomenon, pointing towards the inefficacy of the usual divergences in certain settings. After that, we bring into play the Wasserstein distance, which we prove doesn’t suffer from the same behaviour, and provide a first step on an algorithm that tries to approximately optimize this distance.

Relevant papers:

Towards Principled Methods for Training Generative Adversarial Networks

Wasserstein GAN

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

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cabinet of Natural History Mathematical Physics Seminar Graduate Workshop in Economic and Social History Mini Courses in Theoretical Computer Science home German Society Speaker Events

Other talks

Visual hallucinations in Parkinson’s disease - imbalances in top-down vs. bottom up information processing Sir Richard Stone Annual Lecture: The Emergence of Weak, Despotic and Inclusive States Making Smart Decisions in Systems Design: How to Engineer Decisions in a Connected World? Statistical analysis of biotherapeutic datasets to facilitate early ‘Critical Quality Attribute’ characterization. Prescribing step counts in type 2 diabetes and hypertension:Results of the Step Monitoring to improve ARTERial health trial NatHistFest: the 99th Conversazione and exhibition on the wonders of the natural world.
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity