![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
The goal of this talk is to introduce the Hamiltonian Monte Carlo method -- a physics-inspired algorithm for sampling from Gibbs densities. We focus on the ``idealized'' case, where one can compute continuous trajectories exactly. We show that idealized HMC preserves the target density and we establish its convergence when $f$ is strongly convex.