DMS Applied Mathematics Seminar

Speaker: Wuchen Li (University of South Carolina, https://people.math.sc.edu/wuchen/index.html)

Title: Learning via transport information geometry

Abstract: Recently, optimal transport has many applications in machine learning. In this talk, we introduce dynamical optimal transport on machine learning models. We propose to study these model as a Riemannian manifold with a Wasserstein metric. We call it transport information geometry. Various developments, especially the Fokker-Planck equation and mean field games on learning models, will be introduced. The entropy production of Shannon entropy in AI models will be established. Many numerical examples, including restricted Boltzmann machine and generative adversary network, will be presented.

Location and Time: Zoom,  Friday (Feb 19), 2pm-3pm.

Join from PC, Mac, Linux, iOS or Android: https://auburn.zoom.us/j/88918338743