Event

CANCELLED--------Simon Lacoste-Julien, Université de Montréal

Friday, January 25, 2019 15:30to16:30

THIS SEMINAR HAS BEEN CANCELLED

Title: New Perspectives on Generative Adversarial Networks

Abstract: Generative Adversarial Networks (GANs) are a popular generative modeling approach known for producing appealing samples, but their theoretical properties are not yet fully understood, and they are notably difficult to train. In the first part of this talk, I will provide some insights on why GANs are a more meaningful framework to model high dimensional data like images than the more traditional maximum likelihood approach, interpreting them as “parametric adversarial divergences” and rooting the analysis with statistical decision theory. In the second part of the talk, I will address the difficulty of training GANs from the optimization perspective by importing tools from the mathematical programming literature. I will survey the “variational inequality” framework which contains most formulations of GANs introduced so far, and present theoretical and empirical results on adapting the standard methods (such as the extragradient method) from this literature to the training of GANs.
The talk is based on the following two papers: “Parametric Adversarial Divergences are Good Task Losses for Generative Modeling”, G. Huang, H. Berard, A. Touati, G. Gidel, P. Vincent, S. Lacoste-Julien https://arxiv.org/abs/1708.02511
“A Variational Inequality Perspective on GANs”, G. Gidel, H. Berard, G. Vignoud, P. Vincent, S. Lacoste-Julien https://arxiv.org/abs/1802.10551 to appear at ICLR 2019
 

Back to top