![Geometric Methods in Optimization and Sampling_hi-res logo](/sites/default/files/styles/workshop_banner_sm_1x/public/2023-03/Geometric%20Methods%20in%20Optimization%20and%20Sampling_hi-res.jpg?h=b86da943&itok=A6FwVTMn)
Abstract
This lecture lies at the interface of geometry and optimization. In particular, I'll talk about geodesic convexity and geodesically convex optimization. This class of problems offers a rich and multifaceted class of nonconvex optimization problems that can admit tractable global solutions. I'll provide some background on geodesic convexity and some canonical examples as motivation. Subsequently, I will cover complexity theory of gradient based geodesically convex optimization, culminating with the Riemannian analog of Nesterov's Euclidean accelerated gradient method. I will also highlight some open problems and important directions worthy of future pursui