An Optimization Perspective on Log-concave Sampling

Sinho Chewi

I will give an introduction to the problem of sampling from a strongly log-concave density on Euclidean space through the lens of convex optimization.  In particular, I will focus on the interpretation, due to Jordan, Kinderlehrer, and Otto, of the Langevin diffusion as a Wasserstein gradient flow.

https://www.ias.edu/video/optimization-perspective-log-concave-sampling