Generative Adversarial Networks (GANs): An Analytical Perspective

05/03/2023 12:30 pm - 1:30 pm
CMSA Room G10
Address: CMSA, 20 Garden Street, Cambridge, MA 02138 USA

Speaker: Xin Guo, UC Berkeley

Title: Generative Adversarial Networks (GANs): An Analytical Perspective

Abstract: Generative models have attracted intense interests recently. In this talk, I will discuss one class of generative models, Generative Adversarial Networks (GANs).  I will first provide a gentle review of the mathematical framework behind GANs. I will then proceed to discuss a few challenges in GANs training from an analytical perspective. I will finally report some recent progress for GANs training in terms of its stability and convergence analysis.