Fall 2021

An Introduction to Hamiltonian Monte Carlo Method for Sampling

Tuesday, August 31st, 2021 3:30 pm4:30 pm

Add to Calendar


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.